85 files changed, 2140 insertions, 1848 deletions

diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index a67b6227d272..ca9b9b9bd331 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -67,6 +67,7 @@ header-y += falloc.h
 header-y += fd.h
 header-y += fdreg.h
 header-y += fib_rules.h
+header-y += fiemap.h
 header-y += firewire-cdev.h
 header-y += firewire-constants.h
 header-y += fuse.h
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 45f6297821bd..5fc2ef8d97fa 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -21,6 +21,15 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 
+/* on architectures without dma-mapping capabilities we need to ensure
+ * that the asynchronous path compiles away
+ */
+#ifdef CONFIG_HAS_DMA
+#define __async_inline
+#else
+#define __async_inline __always_inline
+#endif
+
 /**
  * dma_chan_ref - object used to manage dma channels received from the
  *   dmaengine core.
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 77b4a9e46004..6638b8148de7 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -35,8 +35,7 @@ struct linux_binprm{
 #endif
         struct mm_struct *mm;
         unsigned long p; /* current top of mem */
-        unsigned int sh_bang:1,
-                misc_bang:1,
+        unsigned int
                 cred_prepared:1,/* true if creds already prepared (multiple
                                  * preps happen for interpreters) */
                 cap_effective:1;/* true if has elevated effective capabilities,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 3d7bcde2e332..7b73bb8f1970 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -332,22 +332,10 @@ extern int __set_page_dirty_buffers(struct page *page);
 
 static inline void buffer_init(void) {}
 static inline int try_to_free_buffers(struct page *page) { return 1; }
-static inline int sync_blockdev(struct block_device *bdev) { return 0; }
 static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
-static inline void invalidate_bdev(struct block_device *bdev) {}
-
-static inline struct super_block *freeze_bdev(struct block_device *sb)
-{
-        return NULL;
-}
-
-static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
-        return 0;
-}
 
 #endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 499900d0cee7..665fa70e4094 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -15,6 +15,7 @@
 #include <linux/cgroupstats.h>
 #include <linux/prio_heap.h>
 #include <linux/rwsem.h>
+#include <linux/idr.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -22,6 +23,7 @@ struct cgroupfs_root;
 struct cgroup_subsys;
 struct inode;
 struct cgroup;
+struct css_id;
 
 extern int cgroup_init_early(void);
 extern int cgroup_init(void);
@@ -47,18 +49,24 @@ enum cgroup_subsys_id {
 
 /* Per-subsystem/per-cgroup state maintained by the system. */
 struct cgroup_subsys_state {
-        /* The cgroup that this subsystem is attached to. Useful
+        /*
+         * The cgroup that this subsystem is attached to. Useful
          * for subsystems that want to know about the cgroup
-         * hierarchy structure */
+         * hierarchy structure
+         */
         struct cgroup *cgroup;
 
-        /* State maintained by the cgroup system to allow subsystems
+        /*
+         * State maintained by the cgroup system to allow subsystems
          * to be "busy". Should be accessed via css_get(),
-         * css_tryget() and and css_put(). */
+         * css_tryget() and and css_put().
+         */
 
         atomic_t refcnt;
 
         unsigned long flags;
+        /* ID for this css, if possible */
+        struct css_id *id;
 };
 
 /* bits in struct cgroup_subsys_state flags field */
@@ -120,19 +128,26 @@ static inline void css_put(struct cgroup_subsys_state *css)
 enum {
         /* Control Group is dead */
         CGRP_REMOVED,
-        /* Control Group has previously had a child cgroup or a task,
-         * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */
+        /*
+         * Control Group has previously had a child cgroup or a task,
+         * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
+         */
         CGRP_RELEASABLE,
         /* Control Group requires release notifications to userspace */
         CGRP_NOTIFY_ON_RELEASE,
+        /*
+         * A thread in rmdir() is wating for this cgroup.
+         */
+        CGRP_WAIT_ON_RMDIR,
 };
 
 struct cgroup {
         unsigned long flags;            /* "unsigned long" so bitops work */
 
-        /* count users of this cgroup. >0 means busy, but doesn't
-         * necessarily indicate the number of tasks in the
-         * cgroup */
+        /*
+         * count users of this cgroup. >0 means busy, but doesn't
+         * necessarily indicate the number of tasks in the cgroup
+         */
         atomic_t count;
 
         /*
@@ -142,7 +157,7 @@ struct cgroup {
         struct list_head sibling;       /* my parent's children */
         struct list_head children;      /* my children */
 
-        struct cgroup *parent;  /* my parent */
+        struct cgroup *parent;          /* my parent */
         struct dentry *dentry;          /* cgroup fs entry, RCU protected */
 
         /* Private pointers for each registered subsystem */
@@ -177,11 +192,12 @@ struct cgroup {
         struct rcu_head rcu_head;
 };
 
-/* A css_set is a structure holding pointers to a set of
+/*
+ * A css_set is a structure holding pointers to a set of
  * cgroup_subsys_state objects. This saves space in the task struct
  * object and speeds up fork()/exit(), since a single inc/dec and a
- * list_add()/del() can bump the reference count on the entire
- * cgroup set for a task.
+ * list_add()/del() can bump the reference count on the entire cgroup
+ * set for a task.
  */
 
 struct css_set {
@@ -226,13 +242,8 @@ struct cgroup_map_cb {
         void *state;
 };
 
-/* struct cftype:
- *
- * The files in the cgroup filesystem mostly have a very simple read/write
- * handling, some common function will take care of it. Nevertheless some cases
- * (read tasks) are special and therefore I define this structure for every
- * kind of file.
- *
+/*
+ * struct cftype: handler definitions for cgroup control files
  *
  * When reading/writing to a file:
  *      - the cgroup to use is file->f_dentry->d_parent->d_fsdata
@@ -241,10 +252,17 @@ struct cgroup_map_cb {
 
 #define MAX_CFTYPE_NAME 64
 struct cftype {
-        /* By convention, the name should begin with the name of the
-         * subsystem, followed by a period */
+        /*
+         * By convention, the name should begin with the name of the
+         * subsystem, followed by a period
+         */
         char name[MAX_CFTYPE_NAME];
         int private;
+        /*
+         * If not 0, file mode is set to this value, otherwise it will
+         * be figured out automatically
+         */
+        mode_t mode;
 
         /*
          * If non-zero, defines the maximum length of string that can
@@ -319,15 +337,20 @@ struct cgroup_scanner {
         void (*process_task)(struct task_struct *p,
                         struct cgroup_scanner *scan);
         struct ptr_heap *heap;
+        void *data;
 };
 
-/* Add a new file to the given cgroup directory. Should only be
- * called by subsystems from within a populate() method */
+/*
+ * Add a new file to the given cgroup directory. Should only be
+ * called by subsystems from within a populate() method
+ */
 int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
                        const struct cftype *cft);
 
-/* Add a set of new files to the given cgroup directory. Should
- * only be called by subsystems from within a populate() method */
+/*
+ * Add a set of new files to the given cgroup directory. Should
+ * only be called by subsystems from within a populate() method
+ */
 int cgroup_add_files(struct cgroup *cgrp,
                         struct cgroup_subsys *subsys,
                         const struct cftype cft[],
@@ -339,15 +362,18 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen);
 
 int cgroup_task_count(const struct cgroup *cgrp);
 
-/* Return true if the cgroup is a descendant of the current cgroup */
-int cgroup_is_descendant(const struct cgroup *cgrp);
+/* Return true if cgrp is a descendant of the task's cgroup */
+int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);
 
-/* Control Group subsystem type. See Documentation/cgroups.txt for details */
+/*
+ * Control Group subsystem type.
+ * See Documentation/cgroups/cgroups.txt for details
+ */
 
 struct cgroup_subsys {
         struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss,
                                                   struct cgroup *cgrp);
-        void (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
+        int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
         void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
         int (*can_attach)(struct cgroup_subsys *ss,
                           struct cgroup *cgrp, struct task_struct *tsk);
@@ -364,6 +390,11 @@ struct cgroup_subsys {
         int active;
         int disabled;
         int early_init;
+        /*
+         * True if this subsys uses ID. ID is not available before cgroup_init()
+         * (not available in early_init time.)
+         */
+        bool use_id;
 #define MAX_CGROUP_TYPE_NAMELEN 32
         const char *name;
 
@@ -386,6 +417,9 @@ struct cgroup_subsys {
          */
         struct cgroupfs_root *root;
         struct list_head sibling;
+        /* used when use_id == true */
+        struct idr idr;
+        spinlock_t id_lock;
 };
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
@@ -419,7 +453,8 @@ struct cgroup_iter {
         struct list_head *task;
 };
 
-/* To iterate across the tasks in a cgroup:
+/*
+ * To iterate across the tasks in a cgroup:
  *
  * 1) call cgroup_iter_start to intialize an iterator
  *
@@ -428,9 +463,10 @@ struct cgroup_iter {
  *
  * 3) call cgroup_iter_end() to destroy the iterator.
  *
- * Or, call cgroup_scan_tasks() to iterate through every task in a cpuset.
- *    - cgroup_scan_tasks() holds the css_set_lock when calling the test_task()
- *      callback, but not while calling the process_task() callback.
+ * Or, call cgroup_scan_tasks() to iterate through every task in a
+ * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling
+ * the test_task() callback, but not while calling the process_task()
+ * callback.
  */
 void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it);
 struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
@@ -439,6 +475,44 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task(struct cgroup *, struct task_struct *);
 
+/*
+ * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
+ * if cgroup_subsys.use_id == true. It can be used for looking up and scanning.
+ * CSS ID is assigned at cgroup allocation (create) automatically
+ * and removed when subsys calls free_css_id() function. This is because
+ * the lifetime of cgroup_subsys_state is subsys's matter.
+ *
+ * Looking up and scanning function should be called under rcu_read_lock().
+ * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls.
+ * But the css returned by this routine can be "not populated yet" or "being
+ * destroyed". The caller should check css and cgroup's status.
+ */
+
+/*
+ * Typically Called at ->destroy(), or somewhere the subsys frees
+ * cgroup_subsys_state.
+ */
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css);
+
+/* Find a cgroup_subsys_state which has given ID */
+
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id);
+
+/*
+ * Get a cgroup whose id is greater than or equal to id under tree of root.
+ * Returning a cgroup_subsys_state or NULL.
+ */
+struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id,
+                struct cgroup_subsys_state *root, int *foundid);
+
+/* Returns true if root is ancestor of cg */
+bool css_is_ancestor(struct cgroup_subsys_state *cg,
+                     const struct cgroup_subsys_state *root);
+
+/* Get id and depth of css */
+unsigned short css_id(struct cgroup_subsys_state *css);
+unsigned short css_depth(struct cgroup_subsys_state *css);
+
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
diff --git a/include/linux/compat.h b/include/linux/compat.h
index b880864672de..f2ded21f9a3c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -191,6 +191,12 @@ asmlinkage ssize_t compat_sys_readv(unsigned long fd,
                 const struct compat_iovec __user *vec, unsigned long vlen);
 asmlinkage ssize_t compat_sys_writev(unsigned long fd,
                 const struct compat_iovec __user *vec, unsigned long vlen);
+asmlinkage ssize_t compat_sys_preadv(unsigned long fd,
+                const struct compat_iovec __user *vec,
+                unsigned long vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
+                const struct compat_iovec __user *vec,
+                unsigned long vlen, u32 pos_low, u32 pos_high);
 
 int compat_do_execve(char * filename, compat_uptr_t __user *argv,
                 compat_uptr_t __user *envp, struct pt_regs * regs);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c2747ac2ae43..2643d848df90 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -23,7 +23,6 @@
 #include <linux/node.h>
 #include <linux/compiler.h>
 #include <linux/cpumask.h>
-#include <linux/mutex.h>
 
 struct cpu {
         int node_id;            /* The node which contains the CPU */
@@ -103,16 +102,6 @@ extern struct sysdev_class cpu_sysdev_class;
 #ifdef CONFIG_HOTPLUG_CPU
 /* Stop CPUs going up and down. */
 
-static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
-{
-        mutex_lock(cpu_hp_mutex);
-}
-
-static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
-{
-        mutex_unlock(cpu_hp_mutex);
-}
-
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 #define hotcpu_notifier(fn, pri) {                              \
@@ -126,11 +115,6 @@ int cpu_down(unsigned int cpu);
 
 #else           /* CONFIG_HOTPLUG_CPU */
 
-static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
-{ }
-static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
-{ }
-
 #define get_online_cpus()       do { } while (0)
 #define put_online_cpus()       do { } while (0)
 #define hotcpu_notifier(fn, pri)        do { (void)(fn); } while (0)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 2e0d79678deb..05ea1dd7d681 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/cgroup.h>
+#include <linux/mm.h>
 
 #ifdef CONFIG_CPUSETS
 
@@ -29,19 +30,29 @@ void cpuset_init_current_mems_allowed(void);
 void cpuset_update_task_memory_state(void);
 int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
-extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask);
-extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask);
+extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask);
+extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask);
 
-static int inline cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 {
         return number_of_cpusets <= 1 ||
-                __cpuset_zone_allowed_softwall(z, gfp_mask);
+                __cpuset_node_allowed_softwall(node, gfp_mask);
 }
 
-static int inline cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 {
         return number_of_cpusets <= 1 ||
-                __cpuset_zone_allowed_hardwall(z, gfp_mask);
+                __cpuset_node_allowed_hardwall(node, gfp_mask);
+}
+
+static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+{
+        return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask);
+}
+
+static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+{
+        return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask);
 }
 
 extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
@@ -112,6 +123,16 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
         return 1;
 }
 
+static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
+{
+        return 1;
+}
+
+static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
+{
+        return 1;
+}
+
 static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
 {
         return 1;
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 8209e08969f9..66ec05a57955 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -139,6 +139,9 @@ struct target_type {
         dm_ioctl_fn ioctl;
         dm_merge_fn merge;
         dm_busy_fn busy;
+
+        /* For internal device-mapper use. */
+        struct list_head list;
 };
 
 struct io_restrictions {
diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h
index 600c5fb2daad..5e8b11d88f6f 100644
--- a/include/linux/dm-dirty-log.h
+++ b/include/linux/dm-dirty-log.h
@@ -28,6 +28,9 @@ struct dm_dirty_log_type {
         const char *name;
         struct module *module;
 
+        /* For internal device-mapper use */
+        struct list_head list;
+
         int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
                    unsigned argc, char **argv);
         void (*dtr)(struct dm_dirty_log *log);
@@ -113,6 +116,16 @@ struct dm_dirty_log_type {
          */
         int (*status)(struct dm_dirty_log *log, status_type_t status_type,
                       char *result, unsigned maxlen);
+
+        /*
+         * is_remote_recovering is necessary for cluster mirroring. It provides
+         * a way to detect recovery on another node, so we aren't writing
+         * concurrently.  This function is likely to block (when a cluster log
+         * is used).
+         *
+         * Returns: 0, 1
+         */
+        int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region);
 };
 
 int dm_dirty_log_type_register(struct dm_dirty_log_type *type);
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index af1dab41674b..1a455f1f86d7 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -11,6 +11,7 @@
 
 #define DMA_PTE_READ (1)
 #define DMA_PTE_WRITE (2)
+#define DMA_PTE_SNP (1 << 11)
 
 struct intel_iommu;
 struct dmar_domain;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 1956c8d46d32..2e2aa3df170c 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -23,9 +23,6 @@
 
 #include <linux/device.h>
 #include <linux/uio.h>
-#include <linux/kref.h>
-#include <linux/completion.h>
-#include <linux/rcupdate.h>
 #include <linux/dma-mapping.h>
 
 /**
@@ -205,6 +202,7 @@ struct dma_async_tx_descriptor {
 /**
  * struct dma_device - info on the entity supplying DMA services
  * @chancnt: how many DMA channels are supported
+ * @privatecnt: how many DMA channels are requested by dma_request_channel
  * @channels: the list of struct dma_chan
  * @global_node: list_head for global dma_device_list
  * @cap_mask: one or more dma_capability flags
@@ -227,6 +225,7 @@ struct dma_async_tx_descriptor {
 struct dma_device {
 
         unsigned int chancnt;
+        unsigned int privatecnt;
         struct list_head channels;
         struct list_head global_node;
         dma_cap_mask_t  cap_mask;
@@ -291,6 +290,24 @@ static inline void net_dmaengine_put(void)
 }
 #endif
 
+#ifdef CONFIG_ASYNC_TX_DMA
+#define async_dmaengine_get()   dmaengine_get()
+#define async_dmaengine_put()   dmaengine_put()
+#define async_dma_find_channel(type) dma_find_channel(type)
+#else
+static inline void async_dmaengine_get(void)
+{
+}
+static inline void async_dmaengine_put(void)
+{
+}
+static inline struct dma_chan *
+async_dma_find_channel(enum dma_transaction_type type)
+{
+        return NULL;
+}
+#endif
+
 dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
         void *dest, void *src, size_t len);
 dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan,
@@ -337,6 +354,13 @@ __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
         set_bit(tx_type, dstp->bits);
 }
 
+#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask))
+static inline void
+__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
+{
+        clear_bit(tx_type, dstp->bits);
+}
+
 #define dma_cap_zero(mask) __dma_cap_zero(&(mask))
 static inline void __dma_cap_zero(dma_cap_mask_t *dstp)
 {
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index d797dde247f7..c8aad713a046 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -74,4 +74,23 @@ struct dw_dma_slave {
 #define DWC_CFGL_HS_DST_POL     (1 << 18)       /* dst handshake active low */
 #define DWC_CFGL_HS_SRC_POL     (1 << 19)       /* src handshake active low */
 
+/* DMA API extensions */
+struct dw_cyclic_desc {
+        struct dw_desc  **desc;
+        unsigned long   periods;
+        void            (*period_callback)(void *param);
+        void            *period_callback_param;
+};
+
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+                dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+                enum dma_data_direction direction);
+void dw_dma_cyclic_free(struct dma_chan *chan);
+int dw_dma_cyclic_start(struct dma_chan *chan);
+void dw_dma_cyclic_stop(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+
 #endif /* DW_DMAC_H */
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index dd495b8c3091..634a5e5aba3e 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -208,6 +208,7 @@ static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags)
 #define EXT3_STATE_JDATA                0x00000001 /* journaled data exists */
 #define EXT3_STATE_NEW                  0x00000002 /* inode is newly created */
 #define EXT3_STATE_XATTR                0x00000004 /* has in-inode xattrs */
+#define EXT3_STATE_FLUSH_ON_CLOSE       0x00000008
 
 /* Used to pass group descriptor data when online resize is done */
 struct ext3_new_group_input {
@@ -893,9 +894,8 @@ extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
                        u64 start, u64 len);
 
 /* ioctl.c */
-extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
-                       unsigned long);
-extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long);
+extern long ext3_ioctl(struct file *, unsigned int, unsigned long);
+extern long ext3_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* namei.c */
 extern int ext3_orphan_add(handle_t *, struct inode *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 61211ad823fe..a09e17c8f5fd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1741,6 +1741,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
 
+extern int current_umask(void);
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -1885,6 +1887,18 @@ extern int fsync_super(struct super_block *);
 extern int fsync_no_super(struct block_device *);
 #else
 static inline void bd_forget(struct inode *inode) {}
+static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline void invalidate_bdev(struct block_device *bdev) {}
+
+static inline struct super_block *freeze_bdev(struct block_device *sb)
+{
+        return NULL;
+}
+
+static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+{
+        return 0;
+}
 #endif
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 18b467dbe278..78a05bfcd8eb 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -4,12 +4,10 @@
 #include <linux/path.h>
 
 struct fs_struct {
-        atomic_t count; /* This usage count is used by check_unsafe_exec() for
-                         * security checking purposes - therefore it may not be
-                         * incremented, except by clone(CLONE_FS).
-                         */
+        int users;
         rwlock_t lock;
         int umask;
+        int in_exec;
         struct path root, pwd;
 };
 
@@ -19,6 +17,8 @@ extern void exit_fs(struct task_struct *);
 extern void set_fs_root(struct fs_struct *, struct path *);
 extern void set_fs_pwd(struct fs_struct *, struct path *);
 extern struct fs_struct *copy_fs_struct(struct fs_struct *);
-extern void put_fs_struct(struct fs_struct *);
+extern void free_fs_struct(struct fs_struct *);
+extern void daemonize_fs_struct(void);
+extern int unshare_fs_struct(void);
 
 #endif /* _LINUX_FS_STRUCT_H */
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
new file mode 100644
index 000000000000..84d3532dd3ea
--- /dev/null
+++ b/include/linux/fscache-cache.h
@@ -0,0 +1,505 @@
+/* General filesystem caching backing cache interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ *      Documentation/filesystems/caching/backend-api.txt
+ *
+ * for a description of the cache backend interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_CACHE_H
+#define _LINUX_FSCACHE_CACHE_H
+
+#include <linux/fscache.h>
+#include <linux/sched.h>
+#include <linux/slow-work.h>
+
+#define NR_MAXCACHES BITS_PER_LONG
+
+struct fscache_cache;
+struct fscache_cache_ops;
+struct fscache_object;
+struct fscache_operation;
+
+/*
+ * cache tag definition
+ */
+struct fscache_cache_tag {
+        struct list_head        link;
+        struct fscache_cache    *cache;         /* cache referred to by this tag */
+        unsigned long           flags;
+#define FSCACHE_TAG_RESERVED    0               /* T if tag is reserved for a cache */
+        atomic_t                usage;
+        char                    name[0];        /* tag name */
+};
+
+/*
+ * cache definition
+ */
+struct fscache_cache {
+        const struct fscache_cache_ops *ops;
+        struct fscache_cache_tag *tag;          /* tag representing this cache */
+        struct kobject          *kobj;          /* system representation of this cache */
+        struct list_head        link;           /* link in list of caches */
+        size_t                  max_index_size; /* maximum size of index data */
+        char                    identifier[36]; /* cache label */
+
+        /* node management */
+        struct work_struct      op_gc;          /* operation garbage collector */
+        struct list_head        object_list;    /* list of data/index objects */
+        struct list_head        op_gc_list;     /* list of ops to be deleted */
+        spinlock_t              object_list_lock;
+        spinlock_t              op_gc_list_lock;
+        atomic_t                object_count;   /* no. of live objects in this cache */
+        struct fscache_object   *fsdef;         /* object for the fsdef index */
+        unsigned long           flags;
+#define FSCACHE_IOERROR         0       /* cache stopped on I/O error */
+#define FSCACHE_CACHE_WITHDRAWN 1       /* cache has been withdrawn */
+};
+
+extern wait_queue_head_t fscache_cache_cleared_wq;
+
+/*
+ * operation to be applied to a cache object
+ * - retrieval initiation operations are done in the context of the process
+ *   that issued them, and not in an async thread pool
+ */
+typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
+typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
+
+struct fscache_operation {
+        union {
+                struct work_struct fast_work;   /* record for fast ops */
+                struct slow_work slow_work;     /* record for (very) slow ops */
+        };
+        struct list_head        pend_link;      /* link in object->pending_ops */
+        struct fscache_object   *object;        /* object to be operated upon */
+
+        unsigned long           flags;
+#define FSCACHE_OP_TYPE         0x000f  /* operation type */
+#define FSCACHE_OP_FAST         0x0001  /* - fast op, processor may not sleep for disk */
+#define FSCACHE_OP_SLOW         0x0002  /* - (very) slow op, processor may sleep for disk */
+#define FSCACHE_OP_MYTHREAD     0x0003  /* - processing is done be issuing thread, not pool */
+#define FSCACHE_OP_WAITING      4       /* cleared when op is woken */
+#define FSCACHE_OP_EXCLUSIVE    5       /* exclusive op, other ops must wait */
+#define FSCACHE_OP_DEAD         6       /* op is now dead */
+
+        atomic_t                usage;
+        unsigned                debug_id;       /* debugging ID */
+
+        /* operation processor callback
+         * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform
+         *   the op in a non-pool thread */
+        fscache_operation_processor_t processor;
+
+        /* operation releaser */
+        fscache_operation_release_t release;
+};
+
+extern atomic_t fscache_op_debug_id;
+extern const struct slow_work_ops fscache_op_slow_work_ops;
+
+extern void fscache_enqueue_operation(struct fscache_operation *);
+extern void fscache_put_operation(struct fscache_operation *);
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation.  The caller must still set flags,
+ * object, either fast_work or slow_work if necessary, and processor if needed.
+ */
+static inline void fscache_operation_init(struct fscache_operation *op,
+                                          fscache_operation_release_t release)
+{
+        atomic_set(&op->usage, 1);
+        op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+        op->release = release;
+        INIT_LIST_HEAD(&op->pend_link);
+}
+
+/**
+ * fscache_operation_init_slow - Do additional initialisation of a slow op
+ * @op: The operation to initialise
+ * @processor: The processor function to assign
+ *
+ * Do additional initialisation of an operation as required for slow work.
+ */
+static inline
+void fscache_operation_init_slow(struct fscache_operation *op,
+                                 fscache_operation_processor_t processor)
+{
+        op->processor = processor;
+        slow_work_init(&op->slow_work, &fscache_op_slow_work_ops);
+}
+
+/*
+ * data read operation
+ */
+struct fscache_retrieval {
+        struct fscache_operation op;
+        struct address_space    *mapping;       /* netfs pages */
+        fscache_rw_complete_t   end_io_func;    /* function to call on I/O completion */
+        void                    *context;       /* netfs read context (pinned) */
+        struct list_head        to_do;          /* list of things to be done by the backend */
+        unsigned long           start_time;     /* time at which retrieval started */
+};
+
+typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op,
+                                             struct page *page,
+                                             gfp_t gfp);
+
+typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op,
+                                              struct list_head *pages,
+                                              unsigned *nr_pages,
+                                              gfp_t gfp);
+
+/**
+ * fscache_get_retrieval - Get an extra reference on a retrieval operation
+ * @op: The retrieval operation to get a reference on
+ *
+ * Get an extra reference on a retrieval operation.
+ */
+static inline
+struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op)
+{
+        atomic_inc(&op->op.usage);
+        return op;
+}
+
+/**
+ * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing
+ * @op: The retrieval operation affected
+ *
+ * Enqueue a retrieval operation for processing by the FS-Cache thread pool.
+ */
+static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op)
+{
+        fscache_enqueue_operation(&op->op);
+}
+
+/**
+ * fscache_put_retrieval - Drop a reference to a retrieval operation
+ * @op: The retrieval operation affected
+ *
+ * Drop a reference to a retrieval operation.
+ */
+static inline void fscache_put_retrieval(struct fscache_retrieval *op)
+{
+        fscache_put_operation(&op->op);
+}
+
+/*
+ * cached page storage work item
+ * - used to do three things:
+ *   - batch writes to the cache
+ *   - do cache writes asynchronously
+ *   - defer writes until cache object lookup completion
+ */
+struct fscache_storage {
+        struct fscache_operation op;
+        pgoff_t                 store_limit;    /* don't write more than this */
+};
+
+/*
+ * cache operations
+ */
+struct fscache_cache_ops {
+        /* name of cache provider */
+        const char *name;
+
+        /* allocate an object record for a cookie */
+        struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+                                               struct fscache_cookie *cookie);
+
+        /* look up the object for a cookie */
+        void (*lookup_object)(struct fscache_object *object);
+
+        /* finished looking up */
+        void (*lookup_complete)(struct fscache_object *object);
+
+        /* increment the usage count on this object (may fail if unmounting) */
+        struct fscache_object *(*grab_object)(struct fscache_object *object);
+
+        /* pin an object in the cache */
+        int (*pin_object)(struct fscache_object *object);
+
+        /* unpin an object in the cache */
+        void (*unpin_object)(struct fscache_object *object);
+
+        /* store the updated auxilliary data on an object */
+        void (*update_object)(struct fscache_object *object);
+
+        /* discard the resources pinned by an object and effect retirement if
+         * necessary */
+        void (*drop_object)(struct fscache_object *object);
+
+        /* dispose of a reference to an object */
+        void (*put_object)(struct fscache_object *object);
+
+        /* sync a cache */
+        void (*sync_cache)(struct fscache_cache *cache);
+
+        /* notification that the attributes of a non-index object (such as
+         * i_size) have changed */
+        int (*attr_changed)(struct fscache_object *object);
+
+        /* reserve space for an object's data and associated metadata */
+        int (*reserve_space)(struct fscache_object *object, loff_t i_size);
+
+        /* request a backing block for a page be read or allocated in the
+         * cache */
+        fscache_page_retrieval_func_t read_or_alloc_page;
+
+        /* request backing blocks for a list of pages be read or allocated in
+         * the cache */
+        fscache_pages_retrieval_func_t read_or_alloc_pages;
+
+        /* request a backing block for a page be allocated in the cache so that
+         * it can be written directly */
+        fscache_page_retrieval_func_t allocate_page;
+
+        /* request backing blocks for pages be allocated in the cache so that
+         * they can be written directly */
+        fscache_pages_retrieval_func_t allocate_pages;
+
+        /* write a page to its backing block in the cache */
+        int (*write_page)(struct fscache_storage *op, struct page *page);
+
+        /* detach backing block from a page (optional)
+         * - must release the cookie lock before returning
+         * - may sleep
+         */
+        void (*uncache_page)(struct fscache_object *object,
+                             struct page *page);
+
+        /* dissociate a cache from all the pages it was backing */
+        void (*dissociate_pages)(struct fscache_cache *cache);
+};
+
+/*
+ * data file or index object cookie
+ * - a file will only appear in one cache
+ * - a request to cache a file may or may not be honoured, subject to
+ *   constraints such as disk space
+ * - indices are created on disk just-in-time
+ */
+struct fscache_cookie {
+        atomic_t                        usage;          /* number of users of this cookie */
+        atomic_t                        n_children;     /* number of children of this cookie */
+        spinlock_t                      lock;
+        struct hlist_head               backing_objects; /* object(s) backing this file/index */
+        const struct fscache_cookie_def *def;           /* definition */
+        struct fscache_cookie           *parent;        /* parent of this entry */
+        void                            *netfs_data;    /* back pointer to netfs */
+        struct radix_tree_root          stores;         /* pages to be stored on this cookie */
+#define FSCACHE_COOKIE_PENDING_TAG      0               /* pages tag: pending write to cache */
+
+        unsigned long                   flags;
+#define FSCACHE_COOKIE_LOOKING_UP       0       /* T if non-index cookie being looked up still */
+#define FSCACHE_COOKIE_CREATING         1       /* T if non-index object being created still */
+#define FSCACHE_COOKIE_NO_DATA_YET      2       /* T if new object with no cached data yet */
+#define FSCACHE_COOKIE_PENDING_FILL     3       /* T if pending initial fill on object */
+#define FSCACHE_COOKIE_FILLING          4       /* T if filling object incrementally */
+#define FSCACHE_COOKIE_UNAVAILABLE      5       /* T if cookie is unavailable (error, etc) */
+};
+
+extern struct fscache_cookie fscache_fsdef_index;
+
+/*
+ * on-disk cache file or index handle
+ */
+struct fscache_object {
+        enum fscache_object_state {
+                FSCACHE_OBJECT_INIT,            /* object in initial unbound state */
+                FSCACHE_OBJECT_LOOKING_UP,      /* looking up object */
+                FSCACHE_OBJECT_CREATING,        /* creating object */
+
+                /* active states */
+                FSCACHE_OBJECT_AVAILABLE,       /* cleaning up object after creation */
+                FSCACHE_OBJECT_ACTIVE,          /* object is usable */
+                FSCACHE_OBJECT_UPDATING,        /* object is updating */
+
+                /* terminal states */
+                FSCACHE_OBJECT_DYING,           /* object waiting for accessors to finish */
+                FSCACHE_OBJECT_LC_DYING,        /* object cleaning up after lookup/create */
+                FSCACHE_OBJECT_ABORT_INIT,      /* abort the init state */
+                FSCACHE_OBJECT_RELEASING,       /* releasing object */
+                FSCACHE_OBJECT_RECYCLING,       /* retiring object */
+                FSCACHE_OBJECT_WITHDRAWING,     /* withdrawing object */
+                FSCACHE_OBJECT_DEAD,            /* object is now dead */
+        } state;
+
+        int                     debug_id;       /* debugging ID */
+        int                     n_children;     /* number of child objects */
+        int                     n_ops;          /* number of ops outstanding on object */
+        int                     n_obj_ops;      /* number of object ops outstanding on object */
+        int                     n_in_progress;  /* number of ops in progress */
+        int                     n_exclusive;    /* number of exclusive ops queued */
+        spinlock_t              lock;           /* state and operations lock */
+
+        unsigned long           lookup_jif;     /* time at which lookup started */
+        unsigned long           event_mask;     /* events this object is interested in */
+        unsigned long           events;         /* events to be processed by this object
+                                                 * (order is important - using fls) */
+#define FSCACHE_OBJECT_EV_REQUEUE       0       /* T if object should be requeued */
+#define FSCACHE_OBJECT_EV_UPDATE        1       /* T if object should be updated */
+#define FSCACHE_OBJECT_EV_CLEARED       2       /* T if accessors all gone */
+#define FSCACHE_OBJECT_EV_ERROR         3       /* T if fatal error occurred during processing */
+#define FSCACHE_OBJECT_EV_RELEASE       4       /* T if netfs requested object release */
+#define FSCACHE_OBJECT_EV_RETIRE        5       /* T if netfs requested object retirement */
+#define FSCACHE_OBJECT_EV_WITHDRAW      6       /* T if cache requested object withdrawal */
+
+        unsigned long           flags;
+#define FSCACHE_OBJECT_LOCK             0       /* T if object is busy being processed */
+#define FSCACHE_OBJECT_PENDING_WRITE    1       /* T if object has pending write */
+#define FSCACHE_OBJECT_WAITING          2       /* T if object is waiting on its parent */
+
+        struct list_head        cache_link;     /* link in cache->object_list */
+        struct hlist_node       cookie_link;    /* link in cookie->backing_objects */
+        struct fscache_cache    *cache;         /* cache that supplied this object */
+        struct fscache_cookie   *cookie;        /* netfs's file/index object */
+        struct fscache_object   *parent;        /* parent object */
+        struct slow_work        work;           /* attention scheduling record */
+        struct list_head        dependents;     /* FIFO of dependent objects */
+        struct list_head        dep_link;       /* link in parent's dependents list */
+        struct list_head        pending_ops;    /* unstarted operations on this object */
+        pgoff_t                 store_limit;    /* current storage limit */
+};
+
+extern const char *fscache_object_states[];
+
+#define fscache_object_is_active(obj)                         \
+        (!test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) &&  \
+         (obj)->state >= FSCACHE_OBJECT_AVAILABLE &&          \
+         (obj)->state < FSCACHE_OBJECT_DYING)
+
+extern const struct slow_work_ops fscache_object_slow_work_ops;
+
+/**
+ * fscache_object_init - Initialise a cache object description
+ * @object: Object description
+ *
+ * Initialise a cache object description to its basic values.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_object_init(struct fscache_object *object,
+                         struct fscache_cookie *cookie,
+                         struct fscache_cache *cache)
+{
+        atomic_inc(&cache->object_count);
+
+        object->state = FSCACHE_OBJECT_INIT;
+        spin_lock_init(&object->lock);
+        INIT_LIST_HEAD(&object->cache_link);
+        INIT_HLIST_NODE(&object->cookie_link);
+        vslow_work_init(&object->work, &fscache_object_slow_work_ops);
+        INIT_LIST_HEAD(&object->dependents);
+        INIT_LIST_HEAD(&object->dep_link);
+        INIT_LIST_HEAD(&object->pending_ops);
+        object->n_children = 0;
+        object->n_ops = object->n_in_progress = object->n_exclusive = 0;
+        object->events = object->event_mask = 0;
+        object->flags = 0;
+        object->store_limit = 0;
+        object->cache = cache;
+        object->cookie = cookie;
+        object->parent = NULL;
+}
+
+extern void fscache_object_lookup_negative(struct fscache_object *object);
+extern void fscache_obtained_object(struct fscache_object *object);
+
+/**
+ * fscache_object_destroyed - Note destruction of an object in a cache
+ * @cache: The cache from which the object came
+ *
+ * Note the destruction and deallocation of an object record in a cache.
+ */
+static inline void fscache_object_destroyed(struct fscache_cache *cache)
+{
+        if (atomic_dec_and_test(&cache->object_count))
+                wake_up_all(&fscache_cache_cleared_wq);
+}
+
+/**
+ * fscache_object_lookup_error - Note an object encountered an error
+ * @object: The object on which the error was encountered
+ *
+ * Note that an object encountered a fatal error (usually an I/O error) and
+ * that it should be withdrawn as soon as possible.
+ */
+static inline void fscache_object_lookup_error(struct fscache_object *object)
+{
+        set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events);
+}
+
+/**
+ * fscache_set_store_limit - Set the maximum size to be stored in an object
+ * @object: The object to set the maximum on
+ * @i_size: The limit to set in bytes
+ *
+ * Set the maximum size an object is permitted to reach, implying the highest
+ * byte that may be written.  Intended to be called by the attr_changed() op.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_set_store_limit(struct fscache_object *object, loff_t i_size)
+{
+        object->store_limit = i_size >> PAGE_SHIFT;
+        if (i_size & ~PAGE_MASK)
+                object->store_limit++;
+}
+
+/**
+ * fscache_end_io - End a retrieval operation on a page
+ * @op: The FS-Cache operation covering the retrieval
+ * @page: The page that was to be fetched
+ * @error: The error code (0 if successful)
+ *
+ * Note the end of an operation to retrieve a page, as covered by a particular
+ * operation record.
+ */
+static inline void fscache_end_io(struct fscache_retrieval *op,
+                                  struct page *page, int error)
+{
+        op->end_io_func(page, op->context, error);
+}
+
+/*
+ * out-of-line cache backend functions
+ */
+extern void fscache_init_cache(struct fscache_cache *cache,
+                               const struct fscache_cache_ops *ops,
+                               const char *idfmt,
+                               ...) __attribute__ ((format (printf, 3, 4)));
+
+extern int fscache_add_cache(struct fscache_cache *cache,
+                             struct fscache_object *fsdef,
+                             const char *tagname);
+extern void fscache_withdraw_cache(struct fscache_cache *cache);
+
+extern void fscache_io_error(struct fscache_cache *cache);
+
+extern void fscache_mark_pages_cached(struct fscache_retrieval *op,
+                                      struct pagevec *pagevec);
+
+extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+                                               const void *data,
+                                               uint16_t datalen);
+
+#endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
new file mode 100644
index 000000000000..6d8ee466e0a0
--- /dev/null
+++ b/include/linux/fscache.h
@@ -0,0 +1,618 @@
+/* General filesystem caching interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ *      Documentation/filesystems/caching/netfs-api.txt
+ *
+ * for a description of the network filesystem interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_H
+#define _LINUX_FSCACHE_H
+
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+
+#if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE)
+#define fscache_available() (1)
+#define fscache_cookie_valid(cookie) (cookie)
+#else
+#define fscache_available() (0)
+#define fscache_cookie_valid(cookie) (0)
+#endif
+
+
+/*
+ * overload PG_private_2 to give us PG_fscache - this is used to indicate that
+ * a page is currently backed by a local disk cache
+ */
+#define PageFsCache(page)               PagePrivate2((page))
+#define SetPageFsCache(page)            SetPagePrivate2((page))
+#define ClearPageFsCache(page)          ClearPagePrivate2((page))
+#define TestSetPageFsCache(page)        TestSetPagePrivate2((page))
+#define TestClearPageFsCache(page)      TestClearPagePrivate2((page))
+
+/* pattern used to fill dead space in an index entry */
+#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79
+
+struct pagevec;
+struct fscache_cache_tag;
+struct fscache_cookie;
+struct fscache_netfs;
+
+typedef void (*fscache_rw_complete_t)(struct page *page,
+                                      void *context,
+                                      int error);
+
+/* result of index entry consultation */
+enum fscache_checkaux {
+        FSCACHE_CHECKAUX_OKAY,          /* entry okay as is */
+        FSCACHE_CHECKAUX_NEEDS_UPDATE,  /* entry requires update */
+        FSCACHE_CHECKAUX_OBSOLETE,      /* entry requires deletion */
+};
+
+/*
+ * fscache cookie definition
+ */
+struct fscache_cookie_def {
+        /* name of cookie type */
+        char name[16];
+
+        /* cookie type */
+        uint8_t type;
+#define FSCACHE_COOKIE_TYPE_INDEX       0
+#define FSCACHE_COOKIE_TYPE_DATAFILE    1
+
+        /* select the cache into which to insert an entry in this index
+         * - optional
+         * - should return a cache identifier or NULL to cause the cache to be
+         *   inherited from the parent if possible or the first cache picked
+         *   for a non-index file if not
+         */
+        struct fscache_cache_tag *(*select_cache)(
+                const void *parent_netfs_data,
+                const void *cookie_netfs_data);
+
+        /* get an index key
+         * - should store the key data in the buffer
+         * - should return the amount of amount stored
+         * - not permitted to return an error
+         * - the netfs data from the cookie being used as the source is
+         *   presented
+         */
+        uint16_t (*get_key)(const void *cookie_netfs_data,
+                            void *buffer,
+                            uint16_t bufmax);
+
+        /* get certain file attributes from the netfs data
+         * - this function can be absent for an index
+         * - not permitted to return an error
+         * - the netfs data from the cookie being used as the source is
+         *   presented
+         */
+        void (*get_attr)(const void *cookie_netfs_data, uint64_t *size);
+
+        /* get the auxilliary data from netfs data
+         * - this function can be absent if the index carries no state data
+         * - should store the auxilliary data in the buffer
+         * - should return the amount of amount stored
+         * - not permitted to return an error
+         * - the netfs data from the cookie being used as the source is
+         *   presented
+         */
+        uint16_t (*get_aux)(const void *cookie_netfs_data,
+                            void *buffer,
+                            uint16_t bufmax);
+
+        /* consult the netfs about the state of an object
+         * - this function can be absent if the index carries no state data
+         * - the netfs data from the cookie being used as the target is
+         *   presented, as is the auxilliary data
+         */
+        enum fscache_checkaux (*check_aux)(void *cookie_netfs_data,
+                                           const void *data,
+                                           uint16_t datalen);
+
+        /* get an extra reference on a read context
+         * - this function can be absent if the completion function doesn't
+         *   require a context
+         */
+        void (*get_context)(void *cookie_netfs_data, void *context);
+
+        /* release an extra reference on a read context
+         * - this function can be absent if the completion function doesn't
+         *   require a context
+         */
+        void (*put_context)(void *cookie_netfs_data, void *context);
+
+        /* indicate pages that now have cache metadata retained
+         * - this function should mark the specified pages as now being cached
+         * - the pages will have been marked with PG_fscache before this is
+         *   called, so this is optional
+         */
+        void (*mark_pages_cached)(void *cookie_netfs_data,
+                                  struct address_space *mapping,
+                                  struct pagevec *cached_pvec);
+
+        /* indicate the cookie is no longer cached
+         * - this function is called when the backing store currently caching
+         *   a cookie is removed
+         * - the netfs should use this to clean up any markers indicating
+         *   cached pages
+         * - this is mandatory for any object that may have data
+         */
+        void (*now_uncached)(void *cookie_netfs_data);
+};
+
+/*
+ * fscache cached network filesystem type
+ * - name, version and ops must be filled in before registration
+ * - all other fields will be set during registration
+ */
+struct fscache_netfs {
+        uint32_t                        version;        /* indexing version */
+        const char                      *name;          /* filesystem name */
+        struct fscache_cookie           *primary_index;
+        struct list_head                link;           /* internal link */
+};
+
+/*
+ * slow-path functions for when there is actually caching available, and the
+ * netfs does actually have a valid token
+ * - these are not to be called directly
+ * - these are undefined symbols when FS-Cache is not configured and the
+ *   optimiser takes care of not using them
+ */
+extern int __fscache_register_netfs(struct fscache_netfs *);
+extern void __fscache_unregister_netfs(struct fscache_netfs *);
+extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *);
+extern void __fscache_release_cache_tag(struct fscache_cache_tag *);
+
+extern struct fscache_cookie *__fscache_acquire_cookie(
+        struct fscache_cookie *,
+        const struct fscache_cookie_def *,
+        void *);
+extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
+extern void __fscache_update_cookie(struct fscache_cookie *);
+extern int __fscache_attr_changed(struct fscache_cookie *);
+extern int __fscache_read_or_alloc_page(struct fscache_cookie *,
+                                        struct page *,
+                                        fscache_rw_complete_t,
+                                        void *,
+                                        gfp_t);
+extern int __fscache_read_or_alloc_pages(struct fscache_cookie *,
+                                         struct address_space *,
+                                         struct list_head *,
+                                         unsigned *,
+                                         fscache_rw_complete_t,
+                                         void *,
+                                         gfp_t);
+extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t);
+extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t);
+extern void __fscache_uncache_page(struct fscache_cookie *, struct page *);
+extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *);
+extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *);
+
+/**
+ * fscache_register_netfs - Register a filesystem as desiring caching services
+ * @netfs: The description of the filesystem
+ *
+ * Register a filesystem as desiring caching services if they're available.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_register_netfs(struct fscache_netfs *netfs)
+{
+        if (fscache_available())
+                return __fscache_register_netfs(netfs);
+        else
+                return 0;
+}
+
+/**
+ * fscache_unregister_netfs - Indicate that a filesystem no longer desires
+ * caching services
+ * @netfs: The description of the filesystem
+ *
+ * Indicate that a filesystem no longer desires caching services for the
+ * moment.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+        if (fscache_available())
+                __fscache_unregister_netfs(netfs);
+}
+
+/**
+ * fscache_lookup_cache_tag - Look up a cache tag
+ * @name: The name of the tag to search for
+ *
+ * Acquire a specific cache referral tag that can be used to select a specific
+ * cache in which to cache an index.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name)
+{
+        if (fscache_available())
+                return __fscache_lookup_cache_tag(name);
+        else
+                return NULL;
+}
+
+/**
+ * fscache_release_cache_tag - Release a cache tag
+ * @tag: The tag to release
+ *
+ * Release a reference to a cache referral tag previously looked up.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+        if (fscache_available())
+                __fscache_release_cache_tag(tag);
+}
+
+/**
+ * fscache_acquire_cookie - Acquire a cookie to represent a cache object
+ * @parent: The cookie that's to be the parent of this one
+ * @def: A description of the cache object, including callback operations
+ * @netfs_data: An arbitrary piece of data to be kept in the cookie to
+ * represent the cache object to the netfs
+ *
+ * This function is used to inform FS-Cache about part of an index hierarchy
+ * that can be used to locate files.  This is done by requesting a cookie for
+ * each index in the path to the file.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cookie *fscache_acquire_cookie(
+        struct fscache_cookie *parent,
+        const struct fscache_cookie_def *def,
+        void *netfs_data)
+{
+        if (fscache_cookie_valid(parent))
+                return __fscache_acquire_cookie(parent, def, netfs_data);
+        else
+                return NULL;
+}
+
+/**
+ * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding
+ * it
+ * @cookie: The cookie being returned
+ * @retire: True if the cache object the cookie represents is to be discarded
+ *
+ * This function returns a cookie to the cache, forcibly discarding the
+ * associated cache object if retire is set to true.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+{
+        if (fscache_cookie_valid(cookie))
+                __fscache_relinquish_cookie(cookie, retire);
+}
+
+/**
+ * fscache_update_cookie - Request that a cache object be updated
+ * @cookie: The cookie representing the cache object
+ *
+ * Request an update of the index data for the cache object associated with the
+ * cookie.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_update_cookie(struct fscache_cookie *cookie)
+{
+        if (fscache_cookie_valid(cookie))
+                __fscache_update_cookie(cookie);
+}
+
+/**
+ * fscache_pin_cookie - Pin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be pinned in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_pin_cookie(struct fscache_cookie *cookie)
+{
+        return -ENOBUFS;
+}
+
+/**
+ * fscache_pin_cookie - Unpin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be unpinned from the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unpin_cookie(struct fscache_cookie *cookie)
+{
+}
+
+/**
+ * fscache_attr_changed - Notify cache that an object's attributes changed
+ * @cookie: The cookie representing the cache object
+ *
+ * Send a notification to the cache indicating that an object's attributes have
+ * changed.  This includes the data size.  These attributes will be obtained
+ * through the get_attr() cookie definition op.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_attr_changed(struct fscache_cookie *cookie)
+{
+        if (fscache_cookie_valid(cookie))
+                return __fscache_attr_changed(cookie);
+        else
+                return -ENOBUFS;
+}
+
+/**
+ * fscache_reserve_space - Reserve data space for a cached object
+ * @cookie: The cookie representing the cache object
+ * @i_size: The amount of space to be reserved
+ *
+ * Reserve an amount of space in the cache for the cache object attached to a
+ * cookie so that a write to that object within the space can always be
+ * honoured.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size)
+{
+        return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_page - Read a page from the cache or allocate a block
+ * in which to store it
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to fill if possible
+ * @end_io_func: The callback to invoke when and if the page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a page from the cache, or if that's not possible make a potential
+ * one-block reservation in the cache into which the page may be stored once
+ * fetched from the server.
+ *
+ * If the page is not backed by the cache object, or if it there's some reason
+ * it can't be, -ENOBUFS will be returned and nothing more will be done for
+ * that page.
+ *
+ * Else, if that page is backed by the cache, a read will be initiated directly
+ * to the netfs's page and 0 will be returned by this function.  The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure.  Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if the page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+                               struct page *page,
+                               fscache_rw_complete_t end_io_func,
+                               void *context,
+                               gfp_t gfp)
+{
+        if (fscache_cookie_valid(cookie))
+                return __fscache_read_or_alloc_page(cookie, page, end_io_func,
+                                                    context, gfp);
+        else
+                return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate
+ * blocks in which to store them
+ * @cookie: The cookie representing the cache object
+ * @mapping: The netfs inode mapping to which the pages will be attached
+ * @pages: A list of potential netfs pages to be filled
+ * @end_io_func: The callback to invoke when and if each page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a set of pages from the cache, or if that's not possible, attempt to
+ * make a potential one-block reservation for each page in the cache into which
+ * that page may be stored once fetched from the server.
+ *
+ * If some pages are not backed by the cache object, or if it there's some
+ * reason they can't be, -ENOBUFS will be returned and nothing more will be
+ * done for that pages.
+ *
+ * Else, if some of the pages are backed by the cache, a read will be initiated
+ * directly to the netfs's page and 0 will be returned by this function.  The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure.  Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if a page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in
+ * regard to different pages, the return values are prioritised in that order.
+ * Any pages submitted for reading are removed from the pages list.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+                                struct address_space *mapping,
+                                struct list_head *pages,
+                                unsigned *nr_pages,
+                                fscache_rw_complete_t end_io_func,
+                                void *context,
+                                gfp_t gfp)
+{
+        if (fscache_cookie_valid(cookie))
+                return __fscache_read_or_alloc_pages(cookie, mapping, pages,
+                                                     nr_pages, end_io_func,
+                                                     context, gfp);
+        else
+                return -ENOBUFS;
+}
+
+/**
+ * fscache_alloc_page - Allocate a block in which to store a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to allocate a page for
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request Allocation a block in the cache in which to store a netfs page
+ * without retrieving any contents from the cache.
+ *
+ * If the page is not backed by a file then -ENOBUFS will be returned and
+ * nothing more will be done, and no reservation will be made.
+ *
+ * Else, a block will be allocated if one wasn't already, and 0 will be
+ * returned
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_alloc_page(struct fscache_cookie *cookie,
+                       struct page *page,
+                       gfp_t gfp)
+{
+        if (fscache_cookie_valid(cookie))
+                return __fscache_alloc_page(cookie, page, gfp);
+        else
+                return -ENOBUFS;
+}
+
+/**
+ * fscache_write_page - Request storage of a page in the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to store
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request the contents of the netfs page be written into the cache.  This
+ * request may be ignored if no cache block is currently allocated, in which
+ * case it will return -ENOBUFS.
+ *
+ * If a cache block was already allocated, a write will be initiated and 0 will
+ * be returned.  The PG_fscache_write page bit is set immediately and will then
+ * be cleared at the completion of the write to indicate the success or failure
+ * of the operation.  Note that the completion may happen before the return.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_write_page(struct fscache_cookie *cookie,
+                       struct page *page,
+                       gfp_t gfp)
+{
+        if (fscache_cookie_valid(cookie))
+                return __fscache_write_page(cookie, page, gfp);
+        else
+                return -ENOBUFS;
+}
+
+/**
+ * fscache_uncache_page - Indicate that caching is no longer required on a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that was being cached.
+ *
+ * Tell the cache that we no longer want a page to be cached and that it should
+ * remove any knowledge of the netfs page it may have.
+ *
+ * Note that this cannot cancel any outstanding I/O operations between this
+ * page and the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_uncache_page(struct fscache_cookie *cookie,
+                          struct page *page)
+{
+        if (fscache_cookie_valid(cookie))
+                __fscache_uncache_page(cookie, page);
+}
+
+/**
+ * fscache_check_page_write - Ask if a page is being writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache if a page is being written to the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+bool fscache_check_page_write(struct fscache_cookie *cookie,
+                              struct page *page)
+{
+        if (fscache_cookie_valid(cookie))
+                return __fscache_check_page_write(cookie, page);
+        return false;
+}
+
+/**
+ * fscache_wait_on_page_write - Wait for a page to complete writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache to wake us up when a page is no longer being written to the
+ * cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_wait_on_page_write(struct fscache_cookie *cookie,
+                                struct page *page)
+{
+        if (fscache_cookie_valid(cookie))
+                __fscache_wait_on_page_write(cookie, page);
+}
+
+#endif /* _LINUX_FSCACHE_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index dd20cd78faa8..0bbc15f54536 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -4,6 +4,7 @@
 #include <linux/mmzone.h>
 #include <linux/stddef.h>
 #include <linux/linkage.h>
+#include <linux/topology.h>
 
 struct vm_area_struct;
 
diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h
index ed21bd3dbd25..29ee2873f4a8 100644
--- a/include/linux/hdreg.h
+++ b/include/linux/hdreg.h
@@ -1,68 +1,6 @@
 #ifndef _LINUX_HDREG_H
 #define _LINUX_HDREG_H
 
-#ifdef __KERNEL__
-#include <linux/ata.h>
-
-/*
- * This file contains some defines for the AT-hd-controller.
- * Various sources.
- */
-
-/* ide.c has its own port definitions in "ide.h" */
-
-#define HD_IRQ          14
-
-/* Hd controller regs. Ref: IBM AT Bios-listing */
-#define HD_DATA         0x1f0           /* _CTL when writing */
-#define HD_ERROR        0x1f1           /* see err-bits */
-#define HD_NSECTOR      0x1f2           /* nr of sectors to read/write */
-#define HD_SECTOR       0x1f3           /* starting sector */
-#define HD_LCYL         0x1f4           /* starting cylinder */
-#define HD_HCYL         0x1f5           /* high byte of starting cyl */
-#define HD_CURRENT      0x1f6           /* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS       0x1f7           /* see status-bits */
-#define HD_FEATURE      HD_ERROR        /* same io address, read=error, write=feature */
-#define HD_PRECOMP      HD_FEATURE      /* obsolete use of this port - predates IDE */
-#define HD_COMMAND      HD_STATUS       /* same io address, read=status, write=cmd */
-
-#define HD_CMD          0x3f6           /* used for resets */
-#define HD_ALTSTATUS    0x3f6           /* same as HD_STATUS but doesn't clear irq */
-
-/* remainder is shared between hd.c, ide.c, ide-cd.c, and the hdparm utility */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT                0x01
-#define INDEX_STAT              0x02
-#define ECC_STAT                0x04    /* Corrected error */
-#define DRQ_STAT                0x08
-#define SEEK_STAT               0x10
-#define SRV_STAT                0x10
-#define WRERR_STAT              0x20
-#define READY_STAT              0x40
-#define BUSY_STAT               0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR                0x01    /* Bad address mark */
-#define ILI_ERR                 0x01    /* Illegal Length Indication (ATAPI) */
-#define TRK0_ERR                0x02    /* couldn't find track 0 */
-#define EOM_ERR                 0x02    /* End Of Media (ATAPI) */
-#define ABRT_ERR                0x04    /* Command aborted */
-#define MCR_ERR                 0x08    /* media change request */
-#define ID_ERR                  0x10    /* ID field not found */
-#define MC_ERR                  0x20    /* media changed */
-#define ECC_ERR                 0x40    /* Uncorrectable ECC error */
-#define BBD_ERR                 0x80    /* pre-EIDE meaning:  block marked bad */
-#define ICRC_ERR                0x80    /* new meaning:  CRC error during transfer */
-#define LFS_ERR                 0xf0    /* Last Failed Sense (ATAPI) */
-
-/* Bits of HD_NSECTOR */
-#define CD                      0x01
-#define IO                      0x02
-#define REL                     0x04
-#define TAG_MASK                0xf8
-#endif /* __KERNEL__ */
-
 #include <linux/types.h>
 
 /*
@@ -191,6 +129,7 @@ typedef struct hd_drive_hob_hdr {
 #define TASKFILE_INVALID                0x7fff
 #endif
 
+#ifndef __KERNEL__
 /* ATA/ATAPI Commands pre T13 Spec */
 #define WIN_NOP                         0x00
 /*
@@ -379,6 +318,7 @@ typedef struct hd_drive_hob_hdr {
 #define SECURITY_ERASE_UNIT             0xBD
 #define SECURITY_FREEZE_LOCK            0xBE
 #define SECURITY_DISABLE_PASSWORD       0xBF
+#endif /* __KERNEL__ */
 
 struct hd_geometry {
       unsigned char heads;
@@ -448,6 +388,7 @@ enum {
 
 #define __NEW_HD_DRIVE_ID
 
+#ifndef __KERNEL__
 /*
  * Structure returned by HDIO_GET_IDENTITY, as per ANSI NCITS ATA6 rev.1b spec.
  *
@@ -699,6 +640,7 @@ struct hd_driveid {
                                          *  7:0 Signature
                                          */
 };
+#endif /* __KERNEL__ */
 
 /*
  * IDE "nice" flags. These are used on a per drive basis to determine
diff --git a/include/linux/hid.h b/include/linux/hid.h
index fa8ee9cef7be..a72876e43589 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -270,6 +270,7 @@ struct hid_item {
 
 #define HID_QUIRK_INVERT                        0x00000001
 #define HID_QUIRK_NOTOUCH                       0x00000002
+#define HID_QUIRK_IGNORE                        0x00000004
 #define HID_QUIRK_NOGET                         0x00000008
 #define HID_QUIRK_BADPAD                        0x00000020
 #define HID_QUIRK_MULTI_INPUT                   0x00000040
@@ -603,12 +604,17 @@ struct hid_ll_driver {
         int (*open)(struct hid_device *hdev);
         void (*close)(struct hid_device *hdev);
 
+        int (*power)(struct hid_device *hdev, int level);
+
         int (*hidinput_input_event) (struct input_dev *idev, unsigned int type,
                         unsigned int code, int value);
 
         int (*parse)(struct hid_device *hdev);
 };
 
+#define PM_HINT_FULLON  1<<5
+#define PM_HINT_NORMAL  1<<1
+
 /* Applications from HID Usage Tables 4/8/99 Version 1.1 */
 /* We ignore a few input applications that are not widely used */
 #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || (a == 0x000d0002))
@@ -641,6 +647,7 @@ int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int
 void hid_output_report(struct hid_report *report, __u8 *data);
 struct hid_device *hid_allocate_device(void);
 int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size);
+int hid_check_keys_pressed(struct hid_device *hid);
 int hid_connect(struct hid_device *hid, unsigned int connect_mask);
 
 /**
@@ -791,21 +798,5 @@ dbg_hid(const char *fmt, ...)
                 __FILE__ , ## arg)
 #endif /* HID_FF */
 
-#ifdef __KERNEL__
-#ifdef CONFIG_HID_COMPAT
-#define HID_COMPAT_LOAD_DRIVER(name)    \
-/* prototype to avoid sparse warning */ \
-extern void hid_compat_##name(void);    \
-void hid_compat_##name(void) { }        \
-EXPORT_SYMBOL(hid_compat_##name)
-#else
-#define HID_COMPAT_LOAD_DRIVER(name)
-#endif /* HID_COMPAT */
-#define HID_COMPAT_CALL_DRIVER(name)    do {    \
-        extern void hid_compat_##name(void);    \
-        hid_compat_##name();                    \
-} while (0)
-#endif /* __KERNEL__ */
-
 #endif
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7ff5c55f9b55..1fcb7126a01f 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -19,8 +19,21 @@ static inline void flush_kernel_dcache_page(struct page *page)
 }
 #endif
 
-#ifdef CONFIG_HIGHMEM
+#include <asm/kmap_types.h>
+
+#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
+
+void debug_kmap_atomic(enum km_type type);
+
+#else
 
+static inline void debug_kmap_atomic(enum km_type type)
+{
+}
+
+#endif
+
+#ifdef CONFIG_HIGHMEM
 #include <asm/highmem.h>
 
 /* declarations for linux/mm/highmem.c */
@@ -44,8 +57,6 @@ static inline void *kmap(struct page *page)
 
 #define kunmap(page) do { (void) (page); } while (0)
 
-#include <asm/kmap_types.h>
-
 static inline void *kmap_atomic(struct page *page, enum km_type idx)
 {
         pagefault_disable();
@@ -187,16 +198,4 @@ static inline void copy_highpage(struct page *to, struct page *from)
         kunmap_atomic(vto, KM_USER1);
 }
 
-#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
-
-void debug_kmap_atomic(enum km_type type);
-
-#else
-
-static inline void debug_kmap_atomic(enum km_type type)
-{
-}
-
-#endif
-
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h
index f6edd522a929..8ace93024d60 100644
--- a/include/linux/i2c/at24.h
+++ b/include/linux/i2c/at24.h
@@ -2,6 +2,7 @@
 #define _LINUX_AT24_H
 
 #include <linux/types.h>
+#include <linux/memory.h>
 
 /*
  * As seen through Linux I2C, differences between the most common types of I2C
@@ -23,6 +24,9 @@ struct at24_platform_data {
 #define AT24_FLAG_READONLY      0x40    /* sysfs-entry will be read-only */
 #define AT24_FLAG_IRUGO         0x20    /* sysfs-entry will be world-readable */
 #define AT24_FLAG_TAKE8ADDR     0x10    /* take always 8 addresses (24c00) */
+
+        void            (*setup)(struct memory_accessor *, void *context);
+        void            *context;
 };
 
 #endif /* _LINUX_AT24_H */
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index 8137f660a5cc..0dc80ef24975 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -218,6 +218,53 @@ int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes);
 
 /*----------------------------------------------------------------------*/
 
+/* Power bus message definitions */
+
+#define DEV_GRP_NULL            0x0
+#define DEV_GRP_P1              0x1
+#define DEV_GRP_P2              0x2
+#define DEV_GRP_P3              0x4
+
+#define RES_GRP_RES             0x0
+#define RES_GRP_PP              0x1
+#define RES_GRP_RC              0x2
+#define RES_GRP_PP_RC           0x3
+#define RES_GRP_PR              0x4
+#define RES_GRP_PP_PR           0x5
+#define RES_GRP_RC_PR           0x6
+#define RES_GRP_ALL             0x7
+
+#define RES_TYPE2_R0            0x0
+
+#define RES_TYPE_ALL            0x7
+
+#define RES_STATE_WRST          0xF
+#define RES_STATE_ACTIVE        0xE
+#define RES_STATE_SLEEP         0x8
+#define RES_STATE_OFF           0x0
+
+/*
+ * Power Bus Message Format ... these can be sent individually by Linux,
+ * but are usually part of downloaded scripts that are run when various
+ * power events are triggered.
+ *
+ *  Broadcast Message (16 Bits):
+ *    DEV_GRP[15:13] MT[12]  RES_GRP[11:9]  RES_TYPE2[8:7] RES_TYPE[6:4]
+ *    RES_STATE[3:0]
+ *
+ *  Singular Message (16 Bits):
+ *    DEV_GRP[15:13] MT[12]  RES_ID[11:4]  RES_STATE[3:0]
+ */
+
+#define MSG_BROADCAST(devgrp, grp, type, type2, state) \
+        ( (devgrp) << 13 | 1 << 12 | (grp) << 9 | (type2) << 7 \
+        | (type) << 4 | (state))
+
+#define MSG_SINGULAR(devgrp, id, state) \
+        ((devgrp) << 13 | 0 << 12 | (id) << 4 | (state))
+
+/*----------------------------------------------------------------------*/
+
 struct twl4030_bci_platform_data {
         int *battery_tmp_tbl;
         unsigned int tblsize;
diff --git a/include/linux/idr.h b/include/linux/idr.h
index dd846df8cd32..e968db71e33a 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -106,6 +106,7 @@ int idr_get_new(struct idr *idp, void *ptr, int *id);
 int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
 int idr_for_each(struct idr *idp,
                  int (*fn)(int id, void *p, void *data), void *data);
+void *idr_get_next(struct idr *idp, int *nextid);
 void *idr_replace(struct idr *idp, void *ptr, int id);
 void idr_remove(struct idr *idp, int id);
 void idr_remove_all(struct idr *idp);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 1d6c71d96ede..77214ead1a36 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -123,7 +123,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define ecap_eim_support(e)     ((e >> 4) & 0x1)
 #define ecap_ir_support(e)      ((e >> 3) & 0x1)
 #define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
-
+#define ecap_sc_support(e)      ((e >> 7) & 0x1) /* Snooping Control */
 
 /* IOTLB_REG */
 #define DMA_TLB_FLUSH_GRANU_OFFSET  60
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 8a7bfb1b6ca0..3af4ffd591b9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -21,6 +21,7 @@
 
 #define IOMMU_READ      (1)
 #define IOMMU_WRITE     (2)
+#define IOMMU_CACHE     (4) /* DMA cache coherency */
 
 struct device;
 
@@ -28,6 +29,8 @@ struct iommu_domain {
         void *priv;
 };
 
+#define IOMMU_CAP_CACHE_COHERENCY       0x1
+
 struct iommu_ops {
         int (*domain_init)(struct iommu_domain *domain);
         void (*domain_destroy)(struct iommu_domain *domain);
@@ -39,6 +42,8 @@ struct iommu_ops {
                       size_t size);
         phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
                                     unsigned long iova);
+        int (*domain_has_cap)(struct iommu_domain *domain,
+                              unsigned long cap);
 };
 
 #ifdef CONFIG_IOMMU_API
@@ -57,6 +62,8 @@ extern void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
                               size_t size);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
                                       unsigned long iova);
+extern int iommu_domain_has_cap(struct iommu_domain *domain,
+                                unsigned long cap);
 
 #else /* CONFIG_IOMMU_API */
 
@@ -107,6 +114,12 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
         return 0;
 }
 
+static inline int domain_has_cap(struct iommu_domain *domain,
+                                 unsigned long cap)
+{
+        return 0;
+}
+
 #endif /* CONFIG_IOMMU_API */
 
 #endif /* __LINUX_IOMMU_H */
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 64246dce5663..53ae4399da2d 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -35,7 +35,7 @@
 #define journal_oom_retry 1
 
 /*
- * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds
+ * Define JBD_PARANOID_IOFAIL to cause a kernel BUG() if ext3 finds
  * certain classes of error which can occur due to failed IOs.  Under
  * normal use we want ext3 to continue after such errors, because
  * hardware _can_ fail, but for debugging purposes when running tests on
@@ -552,6 +552,11 @@ struct transaction_s
          */
         int t_handle_count;
 
+        /*
+         * This transaction is being forced and some process is
+         * waiting for it to finish.
+         */
+        int t_synchronous_commit:1;
 };
 
 /**
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index f3fe34391d8e..792274269f2b 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -13,10 +13,17 @@
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
                          2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
 
+struct module;
+
 #ifdef CONFIG_KALLSYMS
 /* Lookup the address for a symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name);
 
+/* Call a function on each kallsyms symbol in the core kernel */
+int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+                                      unsigned long),
+                            void *data);
+
 extern int kallsyms_lookup_size_offset(unsigned long addr,
                                   unsigned long *symbolsize,
                                   unsigned long *offset);
@@ -43,6 +50,14 @@ static inline unsigned long kallsyms_lookup_name(const char *name)
         return 0;
 }
 
+static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+                                                    struct module *,
+                                                    unsigned long),
+                                          void *data)
+{
+        return 0;
+}
+
 static inline int kallsyms_lookup_size_offset(unsigned long addr,
                                               unsigned long *symbolsize,
                                               unsigned long *offset)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e81f2637fdef..d9e75ec7def5 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -255,6 +255,7 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
         }                                       \
 })
 
+void log_buf_kexec_setup(void);
 #else
 static inline int vprintk(const char *s, va_list args)
         __attribute__ ((format (printf, 1, 0)));
@@ -270,6 +271,9 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \
 /* No effect, but we still get type checking even in the !PRINTK case: */
 #define printk_once(x...) printk(x)
 
+static inline void log_buf_kexec_setup(void)
+{
+}
 #endif
 
 extern int printk_needs_cpu(int cpu);
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 92213a9194e1..d5fa565086d1 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -29,10 +29,15 @@
 #ifdef CONFIG_MODULES
 /* modprobe exit status on success, -ve on error.  Return value
  * usually useless though. */
-extern int request_module(const char * name, ...) __attribute__ ((format (printf, 1, 2)));
-#define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x)))
+extern int __request_module(bool wait, const char *name, ...) \
+        __attribute__((format(printf, 2, 3)));
+#define request_module(mod...) __request_module(true, mod)
+#define request_module_nowait(mod...) __request_module(false, mod)
+#define try_then_request_module(x, mod...) \
+        ((x) ?: (__request_module(false, mod), (x)))
 #else
-static inline int request_module(const char * name, ...) { return -ENOSYS; }
+static inline int request_module(const char *name, ...) { return -ENOSYS; }
+static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; }
 #define try_then_request_module(x, mod...) (x)
 #endif
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 76262d83656b..b450a2628855 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -379,7 +379,7 @@ enum {
         ATA_HORKAGE_BRIDGE_OK   = (1 << 10),    /* no bridge limits */
         ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands
                                                     not multiple of 16 bytes */
-        ATA_HORKAGE_FIRMWARE_WARN = (1 << 12),  /* firwmare update warning */
+        ATA_HORKAGE_FIRMWARE_WARN = (1 << 12),  /* firmware update warning */
         ATA_HORKAGE_1_5_GBPS    = (1 << 13),    /* force 1.5 Gbps */
 
          /* DMA mask for user DMA control: User visible values; DO NOT
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 5a58ea3e91e9..da5a5a1f4cd2 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -364,6 +364,23 @@ do {								\
 
 #endif /* CONFIG_LOCK_STAT */
 
+#ifdef CONFIG_LOCKDEP
+
+/*
+ * On lockdep we dont want the hand-coded irq-enable of
+ * _raw_*_lock_flags() code, because lockdep assumes
+ * that interrupts are not re-enabled during lock-acquire:
+ */
+#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \
+        LOCK_CONTENDED((_lock), (try), (lock))
+
+#else /* CONFIG_LOCKDEP */
+
+#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \
+        lockfl((_lock), (flags))
+
+#endif /* CONFIG_LOCKDEP */
+
 #ifdef CONFIG_GENERIC_HARDIRQS
 extern void early_init_irq_lock_class(void);
 #else
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 326f45c86530..18146c980b68 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -88,9 +88,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
 /*
  * For memory reclaim.
  */
-extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
-extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
-
 extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);
 extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
                                                         int priority);
@@ -104,6 +101,8 @@ struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
                                                       struct zone *zone);
 struct zone_reclaim_stat*
 mem_cgroup_get_reclaim_stat_from_page(struct page *page);
+extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+                                        struct task_struct *p);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 extern int do_swap_account;
@@ -209,16 +208,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
 {
 }
 
-static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
-{
-        return 0;
-}
-
-static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
-{
-        return 0;
-}
-
 static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
 {
         return 0;
@@ -270,6 +259,11 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
         return NULL;
 }
 
+static inline void
+mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+{
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 86a6c0f0518d..37fa19b34ef5 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -100,6 +100,17 @@ enum mem_add_context { BOOT, HOTPLUG };
 #endif
 
 /*
+ * 'struct memory_accessor' is a generic interface to provide
+ * in-kernel access to persistent memory such as i2c or SPI EEPROMs
+ */
+struct memory_accessor {
+        ssize_t (*read)(struct memory_accessor *, char *buf, off_t offset,
+                        size_t count);
+        ssize_t (*write)(struct memory_accessor *, const char *buf,
+                         off_t offset, size_t count);
+};
+
+/*
  * Kernel text modification mutex, used for code patching. Users of this lock
  * can sleep.
  */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index aeabe953ba4f..bff1f0d475c7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1079,7 +1079,7 @@ static inline void setup_per_cpu_pageset(void) {}
 #endif
 
 /* nommu.c */
-extern atomic_t mmap_pages_allocated;
+extern atomic_long_t mmap_pages_allocated;
 
 /* prio_tree.c */
 void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ddadb4defe00..0e80e26ecf21 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -95,6 +95,9 @@ struct page {
         void *virtual;                  /* Kernel virtual address (NULL if
                                            not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
+#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
+        unsigned long debug_flags;      /* Use atomic bitops on this */
+#endif
 };
 
 /*
@@ -175,9 +178,6 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA
         struct mempolicy *vm_policy;    /* NUMA policy for the VMA */
 #endif
-#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
-        unsigned long debug_flags;      /* Use atomic bitops on this */
-#endif
 };
 
 struct core_thread {
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 4e457256bd33..3e7615e9087e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -192,5 +192,10 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host)
         wake_up_process(host->sdio_irq_thread);
 }
 
+struct regulator;
+
+int mmc_regulator_get_ocrmask(struct regulator *supply);
+int mmc_regulator_set_ocr(struct regulator *supply, unsigned short vdd_bit);
+
 #endif
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 26ef24076b76..186ec6ab334d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -764,12 +764,6 @@ extern int numa_zonelist_order_handler(struct ctl_table *, int,
 extern char numa_zonelist_order[];
 #define NUMA_ZONELIST_ORDER_LEN 16      /* string buffer size */
 
-#include <linux/topology.h>
-/* Returns the number of the current Node. */
-#ifndef numa_node_id
-#define numa_node_id()          (cpu_to_node(raw_smp_processor_id()))
-#endif
-
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 
 extern struct pglist_data contig_page_data;
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 830bbcd449d6..3a059298cc19 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -22,6 +22,8 @@ struct proc_mounts {
         int event;
 };
 
+struct fs_struct;
+
 extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
                 struct fs_struct *);
 extern void __put_mnt_ns(struct mnt_namespace *ns);
diff --git a/include/linux/module.h b/include/linux/module.h
index 22d9878e868c..627ac082e2a6 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -248,6 +248,10 @@ struct module
         const unsigned long *crcs;
         unsigned int num_syms;
 
+        /* Kernel parameters. */
+        struct kernel_param *kp;
+        unsigned int num_kp;
+
         /* GPL-only exported symbols. */
         unsigned int num_gpl_syms;
         const struct kernel_symbol *gpl_syms;
@@ -355,6 +359,8 @@ struct module
 #define MODULE_ARCH_INIT {}
 #endif
 
+extern struct mutex module_mutex;
+
 /* FIXME: It'd be nice to isolate modules during init, too, so they
    aren't used before they (may) fail.  But presently too much code
    (IDE & SCSI) require entry into the module during init.*/
@@ -363,10 +369,10 @@ static inline int module_is_live(struct module *mod)
         return mod->state != MODULE_STATE_GOING;
 }
 
-/* Is this address in a module? (second is with no locks, for oops) */
-struct module *module_text_address(unsigned long addr);
 struct module *__module_text_address(unsigned long addr);
-int is_module_address(unsigned long addr);
+struct module *__module_address(unsigned long addr);
+bool is_module_address(unsigned long addr);
+bool is_module_text_address(unsigned long addr);
 
 static inline int within_module_core(unsigned long addr, struct module *mod)
 {
@@ -380,6 +386,31 @@ static inline int within_module_init(unsigned long addr, struct module *mod)
                addr < (unsigned long)mod->module_init + mod->init_size;
 }
 
+/* Search for module by name: must hold module_mutex. */
+struct module *find_module(const char *name);
+
+struct symsearch {
+        const struct kernel_symbol *start, *stop;
+        const unsigned long *crcs;
+        enum {
+                NOT_GPL_ONLY,
+                GPL_ONLY,
+                WILL_BE_GPL_ONLY,
+        } licence;
+        bool unused;
+};
+
+/* Search for an exported symbol by name. */
+const struct kernel_symbol *find_symbol(const char *name,
+                                        struct module **owner,
+                                        const unsigned long **crc,
+                                        bool gplok,
+                                        bool warn);
+
+/* Walk the exported symbol table */
+bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
+                            unsigned int symnum, void *data), void *data);
+
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
@@ -388,6 +419,10 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 /* Look for this name: can be of form module:name. */
 unsigned long module_kallsyms_lookup_name(const char *name);
 
+int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+                                             struct module *, unsigned long),
+                                   void *data);
+
 extern void __module_put_and_exit(struct module *mod, long code)
         __attribute__((noreturn));
 #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code);
@@ -449,6 +484,7 @@ static inline void __module_get(struct module *module)
 #define symbol_put_addr(p) do { } while(0)
 
 #endif /* CONFIG_MODULE_UNLOAD */
+int use_module(struct module *a, struct module *b);
 
 /* This is a #define so the string doesn't get put in every .o file */
 #define module_name(mod)                        \
@@ -495,21 +531,24 @@ search_module_extables(unsigned long addr)
         return NULL;
 }
 
-/* Is this address in a module? */
-static inline struct module *module_text_address(unsigned long addr)
+static inline struct module *__module_address(unsigned long addr)
 {
         return NULL;
 }
 
-/* Is this address in a module? (don't take a lock, we're oopsing) */
 static inline struct module *__module_text_address(unsigned long addr)
 {
         return NULL;
 }
 
-static inline int is_module_address(unsigned long addr)
+static inline bool is_module_address(unsigned long addr)
 {
-        return 0;
+        return false;
+}
+
+static inline bool is_module_text_address(unsigned long addr)
+{
+        return false;
 }
 
 /* Get/put a kernel symbol (calls should be symmetric) */
@@ -564,6 +603,14 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name)
         return 0;
 }
 
+static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+                                                           struct module *,
+                                                           unsigned long),
+                                                 void *data)
+{
+        return 0;
+}
+
 static inline int register_module_notifier(struct notifier_block * nb)
 {
         /* no events will happen anyway, so this can always succeed */
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index e4af3399ef48..a4f0b931846c 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -138,6 +138,16 @@ extern int parse_args(const char *name,
                       unsigned num,
                       int (*unknown)(char *param, char *val));
 
+/* Called by module remove. */
+#ifdef CONFIG_SYSFS
+extern void destroy_params(const struct kernel_param *params, unsigned num);
+#else
+static inline void destroy_params(const struct kernel_param *params,
+                                  unsigned num)
+{
+}
+#endif /* !CONFIG_SYSFS */
+
 /* All the helper functions */
 /* The macros to do compile-time type checking stolen from Jakub
    Jelinek, who IIRC came up with this idea for the 2.4 module init code. */
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 5c42821da2d1..068a0c9946af 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -11,21 +11,11 @@
  */
 #ifdef CONFIG_BLOCK
 
-struct mpage_data {
-        struct bio *bio;
-        sector_t last_block_in_bio;
-        get_block_t *get_block;
-        unsigned use_writepage;
-};
-
 struct writeback_control;
 
-struct bio *mpage_bio_submit(int rw, struct bio *bio);
 int mpage_readpages(struct address_space *mapping, struct list_head *pages,
                                 unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
-int __mpage_writepage(struct page *page, struct writeback_control *wbc,
-                      void *data);
 int mpage_writepages(struct address_space *mapping,
                 struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index bde2557c2a9c..fdffb413b192 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -185,6 +185,9 @@ struct nfs_inode {
         fmode_t                  delegation_state;
         struct rw_semaphore     rwsem;
 #endif /* CONFIG_NFS_V4*/
+#ifdef CONFIG_NFS_FSCACHE
+        struct fscache_cookie   *fscache;
+#endif
         struct inode            vfs_inode;
 };
 
@@ -207,6 +210,8 @@ struct nfs_inode {
 #define NFS_INO_ACL_LRU_SET     (2)             /* Inode is on the LRU list */
 #define NFS_INO_MOUNTPOINT      (3)             /* inode is remote mountpoint */
 #define NFS_INO_FLUSHING        (4)             /* inode is flushing out data */
+#define NFS_INO_FSCACHE         (5)             /* inode can be cached by FS-Cache */
+#define NFS_INO_FSCACHE_LOCK    (6)             /* FS-Cache cookie management lock */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
@@ -260,6 +265,11 @@ static inline int NFS_STALE(const struct inode *inode)
         return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 }
 
+static inline int NFS_FSCACHE(const struct inode *inode)
+{
+        return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
 static inline __u64 NFS_FILEID(const struct inode *inode)
 {
         return NFS_I(inode)->fileid;
@@ -506,6 +516,8 @@ extern int  nfs_readpages(struct file *, struct address_space *,
                 struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
 extern void nfs_readdata_release(void *data);
+extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
+                               struct page *);
 
 /*
  * Allocate nfs_read_data structures
@@ -583,6 +595,7 @@ extern void * nfs_root_data(void);
 #define NFSDBG_CALLBACK         0x0100
 #define NFSDBG_CLIENT           0x0200
 #define NFSDBG_MOUNT            0x0400
+#define NFSDBG_FSCACHE          0x0800
 #define NFSDBG_ALL              0xFFFF
 
 #ifdef __KERNEL__
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 29b1e40dce99..6ad75948cbf7 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -64,6 +64,10 @@ struct nfs_client {
         char                    cl_ipaddr[48];
         unsigned char           cl_id_uniquifier;
 #endif
+
+#ifdef CONFIG_NFS_FSCACHE
+        struct fscache_cookie   *fscache;       /* client index cache cookie */
+#endif
 };
 
 /*
@@ -96,12 +100,19 @@ struct nfs_server {
         unsigned int            acdirmin;
         unsigned int            acdirmax;
         unsigned int            namelen;
+        unsigned int            options;        /* extra options enabled by mount */
+#define NFS_OPTION_FSCACHE      0x00000001      /* - local caching enabled */
 
         struct nfs_fsid         fsid;
         __u64                   maxfilesize;    /* maximum file size */
         unsigned long           mount_time;     /* when this fs was mounted */
         dev_t                   s_dev;          /* superblock dev numbers */
 
+#ifdef CONFIG_NFS_FSCACHE
+        struct nfs_fscache_key  *fscache_key;   /* unique key for superblock */
+        struct fscache_cookie   *fscache;       /* superblock cookie */
+#endif
+
 #ifdef CONFIG_NFS_V4
         u32                     attr_bitmask[2];/* V4 bitmask representing the set
                                                    of attributes supported on this
diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h
index 1cb9a3fed2b3..68b10f5f8907 100644
--- a/include/linux/nfs_iostat.h
+++ b/include/linux/nfs_iostat.h
@@ -116,4 +116,16 @@ enum nfs_stat_eventcounters {
         __NFSIOS_COUNTSMAX,
 };
 
+/*
+ * NFS local caching servicing counters
+ */
+enum nfs_stat_fscachecounters {
+        NFSIOS_FSCACHE_PAGES_READ_OK,
+        NFSIOS_FSCACHE_PAGES_READ_FAIL,
+        NFSIOS_FSCACHE_PAGES_WRITTEN_OK,
+        NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL,
+        NFSIOS_FSCACHE_PAGES_UNCACHED,
+        __NFSIOS_FSCACHEMAX,
+};
+
 #endif  /* _LINUX_NFS_IOSTAT */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index afad7dec1b36..7b370c7cfeff 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -8,6 +8,7 @@ struct mnt_namespace;
 struct uts_namespace;
 struct ipc_namespace;
 struct pid_namespace;
+struct fs_struct;
 
 /*
  * A structure to contain pointers to all per-process
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 61df1779b2a5..62214c7d2d93 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -82,6 +82,7 @@ enum pageflags {
         PG_arch_1,
         PG_reserved,
         PG_private,             /* If pagecache, has fs-private data */
+        PG_private_2,           /* If pagecache, has fs aux data */
         PG_writeback,           /* Page is under writeback */
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
         PG_head,                /* A head page */
@@ -108,6 +109,12 @@ enum pageflags {
         /* Filesystems */
         PG_checked = PG_owner_priv_1,
 
+        /* Two page bits are conscripted by FS-Cache to maintain local caching
+         * state.  These bits are set on pages belonging to the netfs's inodes
+         * when those inodes are being locally cached.
+         */
+        PG_fscache = PG_private_2,      /* page backed by cache */
+
         /* XEN */
         PG_pinned = PG_owner_priv_1,
         PG_savepinned = PG_dirty,
@@ -182,7 +189,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 
 struct page;    /* forward declaration */
 
-TESTPAGEFLAG(Locked, locked)
+TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked)
 PAGEFLAG(Error, error)
 PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
@@ -194,8 +201,6 @@ PAGEFLAG(Checked, checked)		/* Used by some filesystems */
 PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)     /* Xen */
 PAGEFLAG(SavePinned, savepinned);                       /* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
-        __SETPAGEFLAG(Private, private)
 PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 
 __PAGEFLAG(SlobPage, slob_page)
@@ -205,6 +210,16 @@ __PAGEFLAG(SlubFrozen, slub_frozen)
 __PAGEFLAG(SlubDebug, slub_debug)
 
 /*
+ * Private page markings that may be used by the filesystem that owns the page
+ * for its own purposes.
+ * - PG_private and PG_private_2 cause releasepage() and co to be invoked
+ */
+PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
+        __CLEARPAGEFLAG(Private, private)
+PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
+PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+
+/*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
@@ -384,9 +399,10 @@ static inline void __ClearPageTail(struct page *page)
  * these flags set.  It they are, there is a problem.
  */
 #define PAGE_FLAGS_CHECK_AT_FREE \
-        (1 << PG_lru   | 1 << PG_private   | 1 << PG_locked | \
-         1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \
-         1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active | \
+        (1 << PG_lru     | 1 << PG_locked    | \
+         1 << PG_private | 1 << PG_private_2 | \
+         1 << PG_buddy   | 1 << PG_writeback | 1 << PG_reserved | \
+         1 << PG_slab    | 1 << PG_swapcache | 1 << PG_active | \
          __PG_UNEVICTABLE | __PG_MLOCKED)
 
 /*
@@ -397,4 +413,16 @@ static inline void __ClearPageTail(struct page *page)
 #define PAGE_FLAGS_CHECK_AT_PREP        ((1 << NR_PAGEFLAGS) - 1)
 
 #endif /* !__GENERATING_BOUNDS_H */
+
+/**
+ * page_has_private - Determine if page has private stuff
+ * @page: The page to be checked
+ *
+ * Determine if a page has private stuff, indicating that release routines
+ * should be invoked upon it.
+ */
+#define page_has_private(page)                  \
+        ((page)->flags & ((1 << PG_private) |   \
+                          (1 << PG_private_2)))
+
 #endif  /* PAGE_FLAGS_H */
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 602cc1fdee90..7339c7bf7331 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -91,24 +91,23 @@ static inline void page_cgroup_init(void)
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 #include <linux/swap.h>
-extern struct mem_cgroup *
-swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem);
-extern struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent);
+extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
+extern unsigned short lookup_swap_cgroup(swp_entry_t ent);
 extern int swap_cgroup_swapon(int type, unsigned long max_pages);
 extern void swap_cgroup_swapoff(int type);
 #else
 #include <linux/swap.h>
 
 static inline
-struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 {
-        return NULL;
+        return 0;
 }
 
 static inline
-struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+unsigned short lookup_swap_cgroup(swp_entry_t ent)
 {
-        return NULL;
+        return 0;
 }
 
 static inline int
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 01ca0856caff..34da5230faab 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -18,9 +18,14 @@
  * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
  * allocation mode flags.
  */
-#define AS_EIO          (__GFP_BITS_SHIFT + 0)  /* IO error on async write */
-#define AS_ENOSPC       (__GFP_BITS_SHIFT + 1)  /* ENOSPC on async write */
-#define AS_MM_ALL_LOCKS (__GFP_BITS_SHIFT + 2)  /* under mm_take_all_locks() */
+enum mapping_flags {
+        AS_EIO          = __GFP_BITS_SHIFT + 0, /* IO error on async write */
+        AS_ENOSPC       = __GFP_BITS_SHIFT + 1, /* ENOSPC on async write */
+        AS_MM_ALL_LOCKS = __GFP_BITS_SHIFT + 2, /* under mm_take_all_locks() */
+#ifdef CONFIG_UNEVICTABLE_LRU
+        AS_UNEVICTABLE  = __GFP_BITS_SHIFT + 3, /* e.g., ramdisk, SHM_LOCK */
+#endif
+};
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
 {
@@ -33,7 +38,6 @@ static inline void mapping_set_error(struct address_space *mapping, int error)
 }
 
 #ifdef CONFIG_UNEVICTABLE_LRU
-#define AS_UNEVICTABLE  (__GFP_BITS_SHIFT + 2)  /* e.g., ramdisk, SHM_LOCK */
 
 static inline void mapping_set_unevictable(struct address_space *mapping)
 {
@@ -380,6 +384,11 @@ static inline void wait_on_page_writeback(struct page *page)
 extern void end_page_writeback(struct page *page);
 
 /*
+ * Add an arbitrary waiter to a page's wait queue
+ */
+extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+
+/*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *
  * This assumes that two userspace pages are always sufficient.  That's
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index cb14fd260837..170f8b1f22db 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -526,6 +526,7 @@
 #define PCI_DEVICE_ID_AMD_OPUS_7443     0x7443
 #define PCI_DEVICE_ID_AMD_VIPER_7443    0x7443
 #define PCI_DEVICE_ID_AMD_OPUS_7445     0x7445
+#define PCI_DEVICE_ID_AMD_8111_PCI      0x7460
 #define PCI_DEVICE_ID_AMD_8111_LPC      0x7468
 #define PCI_DEVICE_ID_AMD_8111_IDE      0x7469
 #define PCI_DEVICE_ID_AMD_8111_SMBUS2   0x746a
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 98b93ca4db06..67c15653fc23 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -94,6 +94,7 @@ extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
                           struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
+extern void exit_ptrace(struct task_struct *tracer);
 extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 3945f803d514..7c775751392c 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -28,4 +28,4 @@ int pwm_enable(struct pwm_device *pwm);
  */
 void pwm_disable(struct pwm_device *pwm);
 
-#endif /* __ASM_ARCH_PWM_H */
+#endif /* __LINUX_PWM_H */
diff --git a/include/linux/raid/bitmap.h b/include/linux/raid/bitmap.h
deleted file mode 100644
index e98900671ca9..000000000000
--- a/include/linux/raid/bitmap.h
+++ /dev/null
@@ -1,288 +0,0 @@
-/*
- * bitmap.h: Copyright (C) Peter T. Breuer (ptb@ot.uc3m.es) 2003
- *
- * additions: Copyright (C) 2003-2004, Paul Clements, SteelEye Technology, Inc.
- */
-#ifndef BITMAP_H
-#define BITMAP_H 1
-
-#define BITMAP_MAJOR_LO 3
-/* version 4 insists the bitmap is in little-endian order
- * with version 3, it is host-endian which is non-portable
- */
-#define BITMAP_MAJOR_HI 4
-#define BITMAP_MAJOR_HOSTENDIAN 3
-
-#define BITMAP_MINOR 39
-
-/*
- * in-memory bitmap:
- *
- * Use 16 bit block counters to track pending writes to each "chunk".
- * The 2 high order bits are special-purpose, the first is a flag indicating
- * whether a resync is needed.  The second is a flag indicating whether a
- * resync is active.
- * This means that the counter is actually 14 bits:
- *
- * +--------+--------+------------------------------------------------+
- * | resync | resync |               counter                          |
- * | needed | active |                                                |
- * |  (0-1) |  (0-1) |              (0-16383)                         |
- * +--------+--------+------------------------------------------------+
- *
- * The "resync needed" bit is set when:
- *    a '1' bit is read from storage at startup.
- *    a write request fails on some drives
- *    a resync is aborted on a chunk with 'resync active' set
- * It is cleared (and resync-active set) when a resync starts across all drives
- * of the chunk.
- *
- *
- * The "resync active" bit is set when:
- *    a resync is started on all drives, and resync_needed is set.
- *       resync_needed will be cleared (as long as resync_active wasn't already set).
- * It is cleared when a resync completes.
- *
- * The counter counts pending write requests, plus the on-disk bit.
- * When the counter is '1' and the resync bits are clear, the on-disk
- * bit can be cleared aswell, thus setting the counter to 0.
- * When we set a bit, or in the counter (to start a write), if the fields is
- * 0, we first set the disk bit and set the counter to 1.
- *
- * If the counter is 0, the on-disk bit is clear and the stipe is clean
- * Anything that dirties the stipe pushes the counter to 2 (at least)
- * and sets the on-disk bit (lazily).
- * If a periodic sweep find the counter at 2, it is decremented to 1.
- * If the sweep find the counter at 1, the on-disk bit is cleared and the
- * counter goes to zero.
- *
- * Also, we'll hijack the "map" pointer itself and use it as two 16 bit block
- * counters as a fallback when "page" memory cannot be allocated:
- *
- * Normal case (page memory allocated):
- *
- *     page pointer (32-bit)
- *
- *     [ ] ------+
- *               |
- *               +-------> [   ][   ]..[   ] (4096 byte page == 2048 counters)
- *                          c1   c2    c2048
- *
- * Hijacked case (page memory allocation failed):
- *
- *     hijacked page pointer (32-bit)
- *
- *     [                  ][              ] (no page memory allocated)
- *      counter #1 (16-bit) counter #2 (16-bit)
- *
- */
-
-#ifdef __KERNEL__
-
-#define PAGE_BITS (PAGE_SIZE << 3)
-#define PAGE_BIT_SHIFT (PAGE_SHIFT + 3)
-
-typedef __u16 bitmap_counter_t;
-#define COUNTER_BITS 16
-#define COUNTER_BIT_SHIFT 4
-#define COUNTER_BYTE_RATIO (COUNTER_BITS / 8)
-#define COUNTER_BYTE_SHIFT (COUNTER_BIT_SHIFT - 3)
-
-#define NEEDED_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 1)))
-#define RESYNC_MASK ((bitmap_counter_t) (1 << (COUNTER_BITS - 2)))
-#define COUNTER_MAX ((bitmap_counter_t) RESYNC_MASK - 1)
-#define NEEDED(x) (((bitmap_counter_t) x) & NEEDED_MASK)
-#define RESYNC(x) (((bitmap_counter_t) x) & RESYNC_MASK)
-#define COUNTER(x) (((bitmap_counter_t) x) & COUNTER_MAX)
-
-/* how many counters per page? */
-#define PAGE_COUNTER_RATIO (PAGE_BITS / COUNTER_BITS)
-/* same, except a shift value for more efficient bitops */
-#define PAGE_COUNTER_SHIFT (PAGE_BIT_SHIFT - COUNTER_BIT_SHIFT)
-/* same, except a mask value for more efficient bitops */
-#define PAGE_COUNTER_MASK  (PAGE_COUNTER_RATIO - 1)
-
-#define BITMAP_BLOCK_SIZE 512
-#define BITMAP_BLOCK_SHIFT 9
-
-/* how many blocks per chunk? (this is variable) */
-#define CHUNK_BLOCK_RATIO(bitmap) ((bitmap)->chunksize >> BITMAP_BLOCK_SHIFT)
-#define CHUNK_BLOCK_SHIFT(bitmap) ((bitmap)->chunkshift - BITMAP_BLOCK_SHIFT)
-#define CHUNK_BLOCK_MASK(bitmap) (CHUNK_BLOCK_RATIO(bitmap) - 1)
-
-/* when hijacked, the counters and bits represent even larger "chunks" */
-/* there will be 1024 chunks represented by each counter in the page pointers */
-#define PAGEPTR_BLOCK_RATIO(bitmap) \
-                        (CHUNK_BLOCK_RATIO(bitmap) << PAGE_COUNTER_SHIFT >> 1)
-#define PAGEPTR_BLOCK_SHIFT(bitmap) \
-                        (CHUNK_BLOCK_SHIFT(bitmap) + PAGE_COUNTER_SHIFT - 1)
-#define PAGEPTR_BLOCK_MASK(bitmap) (PAGEPTR_BLOCK_RATIO(bitmap) - 1)
-
-/*
- * on-disk bitmap:
- *
- * Use one bit per "chunk" (block set). We do the disk I/O on the bitmap
- * file a page at a time. There's a superblock at the start of the file.
- */
-
-/* map chunks (bits) to file pages - offset by the size of the superblock */
-#define CHUNK_BIT_OFFSET(chunk) ((chunk) + (sizeof(bitmap_super_t) << 3))
-
-#endif
-
-/*
- * bitmap structures:
- */
-
-#define BITMAP_MAGIC 0x6d746962
-
-/* use these for bitmap->flags and bitmap->sb->state bit-fields */
-enum bitmap_state {
-        BITMAP_STALE  = 0x002,  /* the bitmap file is out of date or had -EIO */
-        BITMAP_WRITE_ERROR = 0x004, /* A write error has occurred */
-        BITMAP_HOSTENDIAN = 0x8000,
-};
-
-/* the superblock at the front of the bitmap file -- little endian */
-typedef struct bitmap_super_s {
-        __le32 magic;        /*  0  BITMAP_MAGIC */
-        __le32 version;      /*  4  the bitmap major for now, could change... */
-        __u8  uuid[16];      /*  8  128 bit uuid - must match md device uuid */
-        __le64 events;       /* 24  event counter for the bitmap (1)*/
-        __le64 events_cleared;/*32  event counter when last bit cleared (2) */
-        __le64 sync_size;    /* 40  the size of the md device's sync range(3) */
-        __le32 state;        /* 48  bitmap state information */
-        __le32 chunksize;    /* 52  the bitmap chunk size in bytes */
-        __le32 daemon_sleep; /* 56  seconds between disk flushes */
-        __le32 write_behind; /* 60  number of outstanding write-behind writes */
-
-        __u8  pad[256 - 64]; /* set to zero */
-} bitmap_super_t;
-
-/* notes:
- * (1) This event counter is updated before the eventcounter in the md superblock
- *    When a bitmap is loaded, it is only accepted if this event counter is equal
- *    to, or one greater than, the event counter in the superblock.
- * (2) This event counter is updated when the other one is *if*and*only*if* the
- *    array is not degraded.  As bits are not cleared when the array is degraded,
- *    this represents the last time that any bits were cleared.
- *    If a device is being added that has an event count with this value or
- *    higher, it is accepted as conforming to the bitmap.
- * (3)This is the number of sectors represented by the bitmap, and is the range that
- *    resync happens across.  For raid1 and raid5/6 it is the size of individual
- *    devices.  For raid10 it is the size of the array.
- */
-
-#ifdef __KERNEL__
-
-/* the in-memory bitmap is represented by bitmap_pages */
-struct bitmap_page {
-        /*
-         * map points to the actual memory page
-         */
-        char *map;
-        /*
-         * in emergencies (when map cannot be alloced), hijack the map
-         * pointer and use it as two counters itself
-         */
-        unsigned int hijacked:1;
-        /*
-         * count of dirty bits on the page
-         */
-        unsigned int  count:31;
-};
-
-/* keep track of bitmap file pages that have pending writes on them */
-struct page_list {
-        struct list_head list;
-        struct page *page;
-};
-
-/* the main bitmap structure - one per mddev */
-struct bitmap {
-        struct bitmap_page *bp;
-        unsigned long pages; /* total number of pages in the bitmap */
-        unsigned long missing_pages; /* number of pages not yet allocated */
-
-        mddev_t *mddev; /* the md device that the bitmap is for */
-
-        int counter_bits; /* how many bits per block counter */
-
-        /* bitmap chunksize -- how much data does each bit represent? */
-        unsigned long chunksize;
-        unsigned long chunkshift; /* chunksize = 2^chunkshift (for bitops) */
-        unsigned long chunks; /* total number of data chunks for the array */
-
-        /* We hold a count on the chunk currently being synced, and drop
-         * it when the last block is started.  If the resync is aborted
-         * midway, we need to be able to drop that count, so we remember
-         * the counted chunk..
-         */
-        unsigned long syncchunk;
-
-        __u64   events_cleared;
-        int need_sync;
-
-        /* bitmap spinlock */
-        spinlock_t lock;
-
-        long offset; /* offset from superblock if file is NULL */
-        struct file *file; /* backing disk file */
-        struct page *sb_page; /* cached copy of the bitmap file superblock */
-        struct page **filemap; /* list of cache pages for the file */
-        unsigned long *filemap_attr; /* attributes associated w/ filemap pages */
-        unsigned long file_pages; /* number of pages in the file */
-        int last_page_size; /* bytes in the last page */
-
-        unsigned long flags;
-
-        int allclean;
-
-        unsigned long max_write_behind; /* write-behind mode */
-        atomic_t behind_writes;
-
-        /*
-         * the bitmap daemon - periodically wakes up and sweeps the bitmap
-         * file, cleaning up bits and flushing out pages to disk as necessary
-         */
-        unsigned long daemon_lastrun; /* jiffies of last run */
-        unsigned long daemon_sleep; /* how many seconds between updates? */
-        unsigned long last_end_sync; /* when we lasted called end_sync to
-                                      * update bitmap with resync progress */
-
-        atomic_t pending_writes; /* pending writes to the bitmap file */
-        wait_queue_head_t write_wait;
-        wait_queue_head_t overflow_wait;
-
-};
-
-/* the bitmap API */
-
-/* these are used only by md/bitmap */
-int  bitmap_create(mddev_t *mddev);
-void bitmap_flush(mddev_t *mddev);
-void bitmap_destroy(mddev_t *mddev);
-
-void bitmap_print_sb(struct bitmap *bitmap);
-void bitmap_update_sb(struct bitmap *bitmap);
-
-int  bitmap_setallbits(struct bitmap *bitmap);
-void bitmap_write_all(struct bitmap *bitmap);
-
-void bitmap_dirty_bits(struct bitmap *bitmap, unsigned long s, unsigned long e);
-
-/* these are exported */
-int bitmap_startwrite(struct bitmap *bitmap, sector_t offset,
-                        unsigned long sectors, int behind);
-void bitmap_endwrite(struct bitmap *bitmap, sector_t offset,
-                        unsigned long sectors, int success, int behind);
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int degraded);
-void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted);
-void bitmap_close_sync(struct bitmap *bitmap);
-void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);
-
-void bitmap_unplug(struct bitmap *bitmap);
-void bitmap_daemon_work(struct bitmap *bitmap);
-#endif
-
-#endif
diff --git a/include/linux/raid/linear.h b/include/linux/raid/linear.h
deleted file mode 100644
index f38b9c586afb..000000000000
--- a/include/linux/raid/linear.h
+++ /dev/null
@@ -1,31 +0,0 @@
-#ifndef _LINEAR_H
-#define _LINEAR_H
-
-#include <linux/raid/md.h>
-
-struct dev_info {
-        mdk_rdev_t      *rdev;
-        sector_t        num_sectors;
-        sector_t        start_sector;
-};
-
-typedef struct dev_info dev_info_t;
-
-struct linear_private_data
-{
-        struct linear_private_data *prev;       /* earlier version */
-        dev_info_t              **hash_table;
-        sector_t                spacing;
-        sector_t                array_sectors;
-        int                     sector_shift;   /* shift before dividing
-                                                 * by spacing
-                                                 */
-        dev_info_t              disks[0];
-};
-
-
-typedef struct linear_private_data linear_conf_t;
-
-#define mddev_to_conf(mddev) ((linear_conf_t *) mddev->private)
-
-#endif
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
deleted file mode 100644
index 82bea14cae1a..000000000000
--- a/include/linux/raid/md.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
-   md.h : Multiple Devices driver for Linux
-          Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-          Copyright (C) 1994-96 Marc ZYNGIER
-          <zyngier@ufr-info-p7.ibp.fr> or
-          <maz@gloups.fdn.fr>
-          
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2, or (at your option)
-   any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
-*/
-
-#ifndef _MD_H
-#define _MD_H
-
-#include <linux/blkdev.h>
-#include <linux/seq_file.h>
-
-/*
- * 'md_p.h' holds the 'physical' layout of RAID devices
- * 'md_u.h' holds the user <=> kernel API
- *
- * 'md_k.h' holds kernel internal definitions
- */
-
-#include <linux/raid/md_p.h>
-#include <linux/raid/md_u.h>
-#include <linux/raid/md_k.h>
-
-#ifdef CONFIG_MD
-
-/*
- * Different major versions are not compatible.
- * Different minor versions are only downward compatible.
- * Different patchlevel versions are downward and upward compatible.
- */
-#define MD_MAJOR_VERSION                0
-#define MD_MINOR_VERSION                90
-/*
- * MD_PATCHLEVEL_VERSION indicates kernel functionality.
- * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
- *     and major_version/minor_version accordingly
- * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
- *     in the super status byte
- * >=3 means that bitmap superblock version 4 is supported, which uses
- *     little-ending representation rather than host-endian
- */
-#define MD_PATCHLEVEL_VERSION           3
-
-extern int mdp_major;
-
-extern int register_md_personality(struct mdk_personality *p);
-extern int unregister_md_personality(struct mdk_personality *p);
-extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev),
-                                mddev_t *mddev, const char *name);
-extern void md_unregister_thread(mdk_thread_t *thread);
-extern void md_wakeup_thread(mdk_thread_t *thread);
-extern void md_check_recovery(mddev_t *mddev);
-extern void md_write_start(mddev_t *mddev, struct bio *bi);
-extern void md_write_end(mddev_t *mddev);
-extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
-extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
-
-extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
-                           sector_t sector, int size, struct page *page);
-extern void md_super_wait(mddev_t *mddev);
-extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
-                        struct page *page, int rw);
-extern void md_do_sync(mddev_t *mddev);
-extern void md_new_event(mddev_t *mddev);
-extern int md_allow_write(mddev_t *mddev);
-extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
-
-#endif /* CONFIG_MD */
-#endif 
-
diff --git a/include/linux/raid/md_k.h b/include/linux/raid/md_k.h
deleted file mode 100644
index 9743e4dbc918..000000000000
--- a/include/linux/raid/md_k.h
+++ /dev/null
@@ -1,402 +0,0 @@
-/*
-   md_k.h : kernel internal structure of the Linux MD driver
-          Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-          
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2, or (at your option)
-   any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
-*/
-
-#ifndef _MD_K_H
-#define _MD_K_H
-
-/* and dm-bio-list.h is not under include/linux because.... ??? */
-#include "../../../drivers/md/dm-bio-list.h"
-
-#ifdef CONFIG_BLOCK
-
-#define LEVEL_MULTIPATH         (-4)
-#define LEVEL_LINEAR            (-1)
-#define LEVEL_FAULTY            (-5)
-
-/* we need a value for 'no level specified' and 0
- * means 'raid0', so we need something else.  This is
- * for internal use only
- */
-#define LEVEL_NONE              (-1000000)
-
-#define MaxSector (~(sector_t)0)
-
-typedef struct mddev_s mddev_t;
-typedef struct mdk_rdev_s mdk_rdev_t;
-
-/*
- * options passed in raidrun:
- */
-
-/* Currently this must fit in an 'int' */
-#define MAX_CHUNK_SIZE (1<<30)
-
-/*
- * MD's 'extended' device
- */
-struct mdk_rdev_s
-{
-        struct list_head same_set;      /* RAID devices within the same set */
-
-        sector_t size;                  /* Device size (in blocks) */
-        mddev_t *mddev;                 /* RAID array if running */
-        long last_events;               /* IO event timestamp */
-
-        struct block_device *bdev;      /* block device handle */
-
-        struct page     *sb_page;
-        int             sb_loaded;
-        __u64           sb_events;
-        sector_t        data_offset;    /* start of data in array */
-        sector_t        sb_start;       /* offset of the super block (in 512byte sectors) */
-        int             sb_size;        /* bytes in the superblock */
-        int             preferred_minor;        /* autorun support */
-
-        struct kobject  kobj;
-
-        /* A device can be in one of three states based on two flags:
-         * Not working:   faulty==1 in_sync==0
-         * Fully working: faulty==0 in_sync==1
-         * Working, but not
-         * in sync with array
-         *                faulty==0 in_sync==0
-         *
-         * It can never have faulty==1, in_sync==1
-         * This reduces the burden of testing multiple flags in many cases
-         */
-
-        unsigned long   flags;
-#define Faulty          1               /* device is known to have a fault */
-#define In_sync         2               /* device is in_sync with rest of array */
-#define WriteMostly     4               /* Avoid reading if at all possible */
-#define BarriersNotsupp 5               /* BIO_RW_BARRIER is not supported */
-#define AllReserved     6               /* If whole device is reserved for
-                                         * one array */
-#define AutoDetected    7               /* added by auto-detect */
-#define Blocked         8               /* An error occured on an externally
-                                         * managed array, don't allow writes
-                                         * until it is cleared */
-#define StateChanged    9               /* Faulty or Blocked has changed during
-                                         * interrupt, so it needs to be
-                                         * notified by the thread */
-        wait_queue_head_t blocked_wait;
-
-        int desc_nr;                    /* descriptor index in the superblock */
-        int raid_disk;                  /* role of device in array */
-        int saved_raid_disk;            /* role that device used to have in the
-                                         * array and could again if we did a partial
-                                         * resync from the bitmap
-                                         */
-        sector_t        recovery_offset;/* If this device has been partially
-                                         * recovered, this is where we were
-                                         * up to.
-                                         */
-
-        atomic_t        nr_pending;     /* number of pending requests.
-                                         * only maintained for arrays that
-                                         * support hot removal
-                                         */
-        atomic_t        read_errors;    /* number of consecutive read errors that
-                                         * we have tried to ignore.
-                                         */
-        atomic_t        corrected_errors; /* number of corrected read errors,
-                                           * for reporting to userspace and storing
-                                           * in superblock.
-                                           */
-        struct work_struct del_work;    /* used for delayed sysfs removal */
-
-        struct sysfs_dirent *sysfs_state; /* handle for 'state'
-                                           * sysfs entry */
-};
-
-struct mddev_s
-{
-        void                            *private;
-        struct mdk_personality          *pers;
-        dev_t                           unit;
-        int                             md_minor;
-        struct list_head                disks;
-        unsigned long                   flags;
-#define MD_CHANGE_DEVS  0       /* Some device status has changed */
-#define MD_CHANGE_CLEAN 1       /* transition to or from 'clean' */
-#define MD_CHANGE_PENDING 2     /* superblock update in progress */
-
-        int                             ro;
-
-        struct gendisk                  *gendisk;
-
-        struct kobject                  kobj;
-        int                             hold_active;
-#define UNTIL_IOCTL     1
-#define UNTIL_STOP      2
-
-        /* Superblock information */
-        int                             major_version,
-                                        minor_version,
-                                        patch_version;
-        int                             persistent;
-        int                             external;       /* metadata is
-                                                         * managed externally */
-        char                            metadata_type[17]; /* externally set*/
-        int                             chunk_size;
-        time_t                          ctime, utime;
-        int                             level, layout;
-        char                            clevel[16];
-        int                             raid_disks;
-        int                             max_disks;
-        sector_t                        size; /* used size of component devices */
-        sector_t                        array_sectors; /* exported array size */
-        __u64                           events;
-
-        char                            uuid[16];
-
-        /* If the array is being reshaped, we need to record the
-         * new shape and an indication of where we are up to.
-         * This is written to the superblock.
-         * If reshape_position is MaxSector, then no reshape is happening (yet).
-         */
-        sector_t                        reshape_position;
-        int                             delta_disks, new_level, new_layout, new_chunk;
-
-        struct mdk_thread_s             *thread;        /* management thread */
-        struct mdk_thread_s             *sync_thread;   /* doing resync or reconstruct */
-        sector_t                        curr_resync;    /* last block scheduled */
-        unsigned long                   resync_mark;    /* a recent timestamp */
-        sector_t                        resync_mark_cnt;/* blocks written at resync_mark */
-        sector_t                        curr_mark_cnt; /* blocks scheduled now */
-
-        sector_t                        resync_max_sectors; /* may be set by personality */
-
-        sector_t                        resync_mismatches; /* count of sectors where
-                                                            * parity/replica mismatch found
-                                                            */
-
-        /* allow user-space to request suspension of IO to regions of the array */
-        sector_t                        suspend_lo;
-        sector_t                        suspend_hi;
-        /* if zero, use the system-wide default */
-        int                             sync_speed_min;
-        int                             sync_speed_max;
-
-        /* resync even though the same disks are shared among md-devices */
-        int                             parallel_resync;
-
-        int                             ok_start_degraded;
-        /* recovery/resync flags 
-         * NEEDED:   we might need to start a resync/recover
-         * RUNNING:  a thread is running, or about to be started
-         * SYNC:     actually doing a resync, not a recovery
-         * RECOVER:  doing recovery, or need to try it.
-         * INTR:     resync needs to be aborted for some reason
-         * DONE:     thread is done and is waiting to be reaped
-         * REQUEST:  user-space has requested a sync (used with SYNC)
-         * CHECK:    user-space request for for check-only, no repair
-         * RESHAPE:  A reshape is happening
-         *
-         * If neither SYNC or RESHAPE are set, then it is a recovery.
-         */
-#define MD_RECOVERY_RUNNING     0
-#define MD_RECOVERY_SYNC        1
-#define MD_RECOVERY_RECOVER     2
-#define MD_RECOVERY_INTR        3
-#define MD_RECOVERY_DONE        4
-#define MD_RECOVERY_NEEDED      5
-#define MD_RECOVERY_REQUESTED   6
-#define MD_RECOVERY_CHECK       7
-#define MD_RECOVERY_RESHAPE     8
-#define MD_RECOVERY_FROZEN      9
-
-        unsigned long                   recovery;
-        int                             recovery_disabled; /* if we detect that recovery
-                                                            * will always fail, set this
-                                                            * so we don't loop trying */
-
-        int                             in_sync;        /* know to not need resync */
-        struct mutex                    reconfig_mutex;
-        atomic_t                        active;         /* general refcount */
-        atomic_t                        openers;        /* number of active opens */
-
-        int                             changed;        /* true if we might need to reread partition info */
-        int                             degraded;       /* whether md should consider
-                                                         * adding a spare
-                                                         */
-        int                             barriers_work;  /* initialised to true, cleared as soon
-                                                         * as a barrier request to slave
-                                                         * fails.  Only supported
-                                                         */
-        struct bio                      *biolist;       /* bios that need to be retried
-                                                         * because BIO_RW_BARRIER is not supported
-                                                         */
-
-        atomic_t                        recovery_active; /* blocks scheduled, but not written */
-        wait_queue_head_t               recovery_wait;
-        sector_t                        recovery_cp;
-        sector_t                        resync_min;     /* user requested sync
-                                                         * starts here */
-        sector_t                        resync_max;     /* resync should pause
-                                                         * when it gets here */
-
-        struct sysfs_dirent             *sysfs_state;   /* handle for 'array_state'
-                                                         * file in sysfs.
-                                                         */
-        struct sysfs_dirent             *sysfs_action;  /* handle for 'sync_action' */
-
-        struct work_struct del_work;    /* used for delayed sysfs removal */
-
-        spinlock_t                      write_lock;
-        wait_queue_head_t               sb_wait;        /* for waiting on superblock updates */
-        atomic_t                        pending_writes; /* number of active superblock writes */
-
-        unsigned int                    safemode;       /* if set, update "clean" superblock
-                                                         * when no writes pending.
-                                                         */ 
-        unsigned int                    safemode_delay;
-        struct timer_list               safemode_timer;
-        atomic_t                        writes_pending; 
-        struct request_queue            *queue; /* for plugging ... */
-
-        atomic_t                        write_behind; /* outstanding async IO */
-        unsigned int                    max_write_behind; /* 0 = sync */
-
-        struct bitmap                   *bitmap; /* the bitmap for the device */
-        struct file                     *bitmap_file; /* the bitmap file */
-        long                            bitmap_offset; /* offset from superblock of
-                                                        * start of bitmap. May be
-                                                        * negative, but not '0'
-                                                        */
-        long                            default_bitmap_offset; /* this is the offset to use when
-                                                                * hot-adding a bitmap.  It should
-                                                                * eventually be settable by sysfs.
-                                                                */
-
-        struct list_head                all_mddevs;
-};
-
-
-static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev)
-{
-        int faulty = test_bit(Faulty, &rdev->flags);
-        if (atomic_dec_and_test(&rdev->nr_pending) && faulty)
-                set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-}
-
-static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
-{
-        atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
-}
-
-struct mdk_personality
-{
-        char *name;
-        int level;
-        struct list_head list;
-        struct module *owner;
-        int (*make_request)(struct request_queue *q, struct bio *bio);
-        int (*run)(mddev_t *mddev);
-        int (*stop)(mddev_t *mddev);
-        void (*status)(struct seq_file *seq, mddev_t *mddev);
-        /* error_handler must set ->faulty and clear ->in_sync
-         * if appropriate, and should abort recovery if needed 
-         */
-        void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev);
-        int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev);
-        int (*hot_remove_disk) (mddev_t *mddev, int number);
-        int (*spare_active) (mddev_t *mddev);
-        sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
-        int (*resize) (mddev_t *mddev, sector_t sectors);
-        int (*check_reshape) (mddev_t *mddev);
-        int (*start_reshape) (mddev_t *mddev);
-        int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
-        /* quiesce moves between quiescence states
-         * 0 - fully active
-         * 1 - no new requests allowed
-         * others - reserved
-         */
-        void (*quiesce) (mddev_t *mddev, int state);
-};
-
-
-struct md_sysfs_entry {
-        struct attribute attr;
-        ssize_t (*show)(mddev_t *, char *);
-        ssize_t (*store)(mddev_t *, const char *, size_t);
-};
-
-
-static inline char * mdname (mddev_t * mddev)
-{
-        return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
-}
-
-/*
- * iterates through some rdev ringlist. It's safe to remove the
- * current 'rdev'. Dont touch 'tmp' though.
- */
-#define rdev_for_each_list(rdev, tmp, head)                             \
-        list_for_each_entry_safe(rdev, tmp, head, same_set)
-
-/*
- * iterates through the 'same array disks' ringlist
- */
-#define rdev_for_each(rdev, tmp, mddev)                         \
-        list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set)
-
-#define rdev_for_each_rcu(rdev, mddev)                          \
-        list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)
-
-typedef struct mdk_thread_s {
-        void                    (*run) (mddev_t *mddev);
-        mddev_t                 *mddev;
-        wait_queue_head_t       wqueue;
-        unsigned long           flags;
-        struct task_struct      *tsk;
-        unsigned long           timeout;
-} mdk_thread_t;
-
-#define THREAD_WAKEUP  0
-
-#define __wait_event_lock_irq(wq, condition, lock, cmd)                 \
-do {                                                                    \
-        wait_queue_t __wait;                                            \
-        init_waitqueue_entry(&__wait, current);                         \
-                                                                        \
-        add_wait_queue(&wq, &__wait);                                   \
-        for (;;) {                                                      \
-                set_current_state(TASK_UNINTERRUPTIBLE);                \
-                if (condition)                                          \
-                        break;                                          \
-                spin_unlock_irq(&lock);                                 \
-                cmd;                                                    \
-                schedule();                                             \
-                spin_lock_irq(&lock);                                   \
-        }                                                               \
-        current->state = TASK_RUNNING;                                  \
-        remove_wait_queue(&wq, &__wait);                                \
-} while (0)
-
-#define wait_event_lock_irq(wq, condition, lock, cmd)                   \
-do {                                                                    \
-        if (condition)                                                  \
-                break;                                                  \
-        __wait_event_lock_irq(wq, condition, lock, cmd);                \
-} while (0)
-
-static inline void safe_put_page(struct page *p)
-{
-        if (p) put_page(p);
-}
-
-#endif /* CONFIG_BLOCK */
-#endif
-
diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h
index 7192035fc4b0..fb1abb3367e9 100644
--- a/include/linux/raid/md_u.h
+++ b/include/linux/raid/md_u.h
@@ -15,6 +15,24 @@
 #ifndef _MD_U_H
 #define _MD_U_H
 
+/*
+ * Different major versions are not compatible.
+ * Different minor versions are only downward compatible.
+ * Different patchlevel versions are downward and upward compatible.
+ */
+#define MD_MAJOR_VERSION                0
+#define MD_MINOR_VERSION                90
+/*
+ * MD_PATCHLEVEL_VERSION indicates kernel functionality.
+ * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
+ *     and major_version/minor_version accordingly
+ * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
+ *     in the super status byte
+ * >=3 means that bitmap superblock version 4 is supported, which uses
+ *     little-ending representation rather than host-endian
+ */
+#define MD_PATCHLEVEL_VERSION           3
+
 /* ioctls */
 
 /* status */
@@ -46,6 +64,12 @@
 #define STOP_ARRAY_RO           _IO (MD_MAJOR, 0x33)
 #define RESTART_ARRAY_RW        _IO (MD_MAJOR, 0x34)
 
+/* 63 partitions with the alternate major number (mdp) */
+#define MdpMinorShift 6
+#ifdef __KERNEL__
+extern int mdp_major;
+#endif
+
 typedef struct mdu_version_s {
         int major;
         int minor;
@@ -85,6 +109,17 @@ typedef struct mdu_array_info_s {
 
 } mdu_array_info_t;
 
+/* non-obvious values for 'level' */
+#define LEVEL_MULTIPATH         (-4)
+#define LEVEL_LINEAR            (-1)
+#define LEVEL_FAULTY            (-5)
+
+/* we need a value for 'no level specified' and 0
+ * means 'raid0', so we need something else.  This is
+ * for internal use only
+ */
+#define LEVEL_NONE              (-1000000)
+
 typedef struct mdu_disk_info_s {
         /*
          * configuration/status of one particular disk
diff --git a/include/linux/raid/multipath.h b/include/linux/raid/multipath.h
deleted file mode 100644
index 6f53fc177a47..000000000000
--- a/include/linux/raid/multipath.h
+++ /dev/null
@@ -1,42 +0,0 @@
-#ifndef _MULTIPATH_H
-#define _MULTIPATH_H
-
-#include <linux/raid/md.h>
-
-struct multipath_info {
-        mdk_rdev_t      *rdev;
-};
-
-struct multipath_private_data {
-        mddev_t                 *mddev;
-        struct multipath_info   *multipaths;
-        int                     raid_disks;
-        int                     working_disks;
-        spinlock_t              device_lock;
-        struct list_head        retry_list;
-
-        mempool_t               *pool;
-};
-
-typedef struct multipath_private_data multipath_conf_t;
-
-/*
- * this is the only point in the RAID code where we violate
- * C type safety. mddev->private is an 'opaque' pointer.
- */
-#define mddev_to_conf(mddev) ((multipath_conf_t *) mddev->private)
-
-/*
- * this is our 'private' 'collective' MULTIPATH buffer head.
- * it contains information about what kind of IO operations were started
- * for this MULTIPATH operation, and about their status:
- */
-
-struct multipath_bh {
-        mddev_t                 *mddev;
-        struct bio              *master_bio;
-        struct bio              bio;
-        int                     path;
-        struct list_head        retry_list;
-};
-#endif
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
new file mode 100644
index 000000000000..d92480f8285c
--- /dev/null
+++ b/include/linux/raid/pq.h
@@ -0,0 +1,132 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright 2003 H. Peter Anvin - All Rights Reserved
+ *
+ *   This program is free software; you can redistribute it and/or modify
+ *   it under the terms of the GNU General Public License as published by
+ *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
+ *   (at your option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+#ifndef LINUX_RAID_RAID6_H
+#define LINUX_RAID_RAID6_H
+
+#ifdef __KERNEL__
+
+/* Set to 1 to use kernel-wide empty_zero_page */
+#define RAID6_USE_EMPTY_ZERO_PAGE 0
+#include <linux/blkdev.h>
+
+/* We need a pre-zeroed page... if we don't want to use the kernel-provided
+   one define it here */
+#if RAID6_USE_EMPTY_ZERO_PAGE
+# define raid6_empty_zero_page empty_zero_page
+#else
+extern const char raid6_empty_zero_page[PAGE_SIZE];
+#endif
+
+#else /* ! __KERNEL__ */
+/* Used for testing in user space */
+
+#include <errno.h>
+#include <inttypes.h>
+#include <limits.h>
+#include <stddef.h>
+#include <sys/mman.h>
+#include <sys/types.h>
+
+/* Not standard, but glibc defines it */
+#define BITS_PER_LONG __WORDSIZE
+
+typedef uint8_t  u8;
+typedef uint16_t u16;
+typedef uint32_t u32;
+typedef uint64_t u64;
+
+#ifndef PAGE_SIZE
+# define PAGE_SIZE 4096
+#endif
+extern const char raid6_empty_zero_page[PAGE_SIZE];
+
+#define __init
+#define __exit
+#define __attribute_const__ __attribute__((const))
+#define noinline __attribute__((noinline))
+
+#define preempt_enable()
+#define preempt_disable()
+#define cpu_has_feature(x) 1
+#define enable_kernel_altivec()
+#define disable_kernel_altivec()
+
+#define EXPORT_SYMBOL(sym)
+#define MODULE_LICENSE(licence)
+#define subsys_initcall(x)
+#define module_exit(x)
+#endif /* __KERNEL__ */
+
+/* Routine choices */
+struct raid6_calls {
+        void (*gen_syndrome)(int, size_t, void **);
+        int  (*valid)(void);    /* Returns 1 if this routine set is usable */
+        const char *name;       /* Name of this routine set */
+        int prefer;             /* Has special performance attribute */
+};
+
+/* Selected algorithm */
+extern struct raid6_calls raid6_call;
+
+/* Algorithm list */
+extern const struct raid6_calls * const raid6_algos[];
+int raid6_select_algo(void);
+
+/* Return values from chk_syndrome */
+#define RAID6_OK        0
+#define RAID6_P_BAD     1
+#define RAID6_Q_BAD     2
+#define RAID6_PQ_BAD    3
+
+/* Galois field tables */
+extern const u8 raid6_gfmul[256][256] __attribute__((aligned(256)));
+extern const u8 raid6_gfexp[256]      __attribute__((aligned(256)));
+extern const u8 raid6_gfinv[256]      __attribute__((aligned(256)));
+extern const u8 raid6_gfexi[256]      __attribute__((aligned(256)));
+
+/* Recovery routines */
+void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
+                       void **ptrs);
+void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs);
+void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+                      void **ptrs);
+
+/* Some definitions to allow code to be compiled for testing in userspace */
+#ifndef __KERNEL__
+
+# define jiffies        raid6_jiffies()
+# define printk         printf
+# define GFP_KERNEL     0
+# define __get_free_pages(x, y) ((unsigned long)mmap(NULL, PAGE_SIZE << (y), \
+                                                     PROT_READ|PROT_WRITE,   \
+                                                     MAP_PRIVATE|MAP_ANONYMOUS,\
+                                                     0, 0))
+# define free_pages(x, y)       munmap((void *)(x), (y)*PAGE_SIZE)
+
+static inline void cpu_relax(void)
+{
+        /* Nothing */
+}
+
+#undef  HZ
+#define HZ 1000
+static inline uint32_t raid6_jiffies(void)
+{
+        struct timeval tv;
+        gettimeofday(&tv, NULL);
+        return tv.tv_sec*1000 + tv.tv_usec/1000;
+}
+
+#endif /* ! __KERNEL__ */
+
+#endif /* LINUX_RAID_RAID6_H */
diff --git a/include/linux/raid/raid0.h b/include/linux/raid/raid0.h
deleted file mode 100644
index fd42aa87c391..000000000000
--- a/include/linux/raid/raid0.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _RAID0_H
-#define _RAID0_H
-
-#include <linux/raid/md.h>
-
-struct strip_zone
-{
-        sector_t zone_start;    /* Zone offset in md_dev (in sectors) */
-        sector_t dev_start;     /* Zone offset in real dev (in sectors) */
-        sector_t sectors;       /* Zone size in sectors */
-        int nb_dev;             /* # of devices attached to the zone */
-        mdk_rdev_t **dev;       /* Devices attached to the zone */
-};
-
-struct raid0_private_data
-{
-        struct strip_zone **hash_table; /* Table of indexes into strip_zone */
-        struct strip_zone *strip_zone;
-        mdk_rdev_t **devlist; /* lists of rdevs, pointed to by strip_zone->dev */
-        int nr_strip_zones;
-
-        sector_t spacing;
-        int sector_shift; /* shift this before divide by spacing */
-};
-
-typedef struct raid0_private_data raid0_conf_t;
-
-#define mddev_to_conf(mddev) ((raid0_conf_t *) mddev->private)
-
-#endif
diff --git a/include/linux/raid/raid1.h b/include/linux/raid/raid1.h
deleted file mode 100644
index 0a9ba7c3302e..000000000000
--- a/include/linux/raid/raid1.h
+++ /dev/null
@@ -1,134 +0,0 @@
-#ifndef _RAID1_H
-#define _RAID1_H
-
-#include <linux/raid/md.h>
-
-typedef struct mirror_info mirror_info_t;
-
-struct mirror_info {
-        mdk_rdev_t      *rdev;
-        sector_t        head_position;
-};
-
-/*
- * memory pools need a pointer to the mddev, so they can force an unplug
- * when memory is tight, and a count of the number of drives that the
- * pool was allocated for, so they know how much to allocate and free.
- * mddev->raid_disks cannot be used, as it can change while a pool is active
- * These two datums are stored in a kmalloced struct.
- */
-
-struct pool_info {
-        mddev_t *mddev;
-        int     raid_disks;
-};
-
-
-typedef struct r1bio_s r1bio_t;
-
-struct r1_private_data_s {
-        mddev_t                 *mddev;
-        mirror_info_t           *mirrors;
-        int                     raid_disks;
-        int                     last_used;
-        sector_t                next_seq_sect;
-        spinlock_t              device_lock;
-
-        struct list_head        retry_list;
-        /* queue pending writes and submit them on unplug */
-        struct bio_list         pending_bio_list;
-        /* queue of writes that have been unplugged */
-        struct bio_list         flushing_bio_list;
-
-        /* for use when syncing mirrors: */
-
-        spinlock_t              resync_lock;
-        int                     nr_pending;
-        int                     nr_waiting;
-        int                     nr_queued;
-        int                     barrier;
-        sector_t                next_resync;
-        int                     fullsync;  /* set to 1 if a full sync is needed,
-                                            * (fresh device added).
-                                            * Cleared when a sync completes.
-                                            */
-
-        wait_queue_head_t       wait_barrier;
-
-        struct pool_info        *poolinfo;
-
-        struct page             *tmppage;
-
-        mempool_t *r1bio_pool;
-        mempool_t *r1buf_pool;
-};
-
-typedef struct r1_private_data_s conf_t;
-
-/*
- * this is the only point in the RAID code where we violate
- * C type safety. mddev->private is an 'opaque' pointer.
- */
-#define mddev_to_conf(mddev) ((conf_t *) mddev->private)
-
-/*
- * this is our 'private' RAID1 bio.
- *
- * it contains information about what kind of IO operations were started
- * for this RAID1 operation, and about their status:
- */
-
-struct r1bio_s {
-        atomic_t                remaining; /* 'have we finished' count,
-                                            * used from IRQ handlers
-                                            */
-        atomic_t                behind_remaining; /* number of write-behind ios remaining
-                                                 * in this BehindIO request
-                                                 */
-        sector_t                sector;
-        int                     sectors;
-        unsigned long           state;
-        mddev_t                 *mddev;
-        /*
-         * original bio going to /dev/mdx
-         */
-        struct bio              *master_bio;
-        /*
-         * if the IO is in READ direction, then this is where we read
-         */
-        int                     read_disk;
-
-        struct list_head        retry_list;
-        struct bitmap_update    *bitmap_update;
-        /*
-         * if the IO is in WRITE direction, then multiple bios are used.
-         * We choose the number when they are allocated.
-         */
-        struct bio              *bios[0];
-        /* DO NOT PUT ANY NEW FIELDS HERE - bios array is contiguously alloced*/
-};
-
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error.  To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio*)1)
-
-/* bits for r1bio.state */
-#define R1BIO_Uptodate  0
-#define R1BIO_IsSync    1
-#define R1BIO_Degraded  2
-#define R1BIO_BehindIO  3
-#define R1BIO_Barrier   4
-#define R1BIO_BarrierRetry 5
-/* For write-behind requests, we call bi_end_io when
- * the last non-write-behind device completes, providing
- * any write was successful.  Otherwise we call when
- * any write-behind write succeeds, otherwise we call
- * with failure when last write completes (and all failed).
- * Record that bi_end_io was called with this flag...
- */
-#define R1BIO_Returned 6
-
-#endif
diff --git a/include/linux/raid/raid10.h b/include/linux/raid/raid10.h
deleted file mode 100644
index e9091cfeb286..000000000000
--- a/include/linux/raid/raid10.h
+++ /dev/null
@@ -1,123 +0,0 @@
-#ifndef _RAID10_H
-#define _RAID10_H
-
-#include <linux/raid/md.h>
-
-typedef struct mirror_info mirror_info_t;
-
-struct mirror_info {
-        mdk_rdev_t      *rdev;
-        sector_t        head_position;
-};
-
-typedef struct r10bio_s r10bio_t;
-
-struct r10_private_data_s {
-        mddev_t                 *mddev;
-        mirror_info_t           *mirrors;
-        int                     raid_disks;
-        spinlock_t              device_lock;
-
-        /* geometry */
-        int                     near_copies;  /* number of copies layed out raid0 style */
-        int                     far_copies;   /* number of copies layed out
-                                               * at large strides across drives
-                                               */
-        int                     far_offset;   /* far_copies are offset by 1 stripe
-                                               * instead of many
-                                               */
-        int                     copies;       /* near_copies * far_copies.
-                                               * must be <= raid_disks
-                                               */
-        sector_t                stride;       /* distance between far copies.
-                                               * This is size / far_copies unless
-                                               * far_offset, in which case it is
-                                               * 1 stripe.
-                                               */
-
-        int chunk_shift; /* shift from chunks to sectors */
-        sector_t chunk_mask;
-
-        struct list_head        retry_list;
-        /* queue pending writes and submit them on unplug */
-        struct bio_list         pending_bio_list;
-
-
-        spinlock_t              resync_lock;
-        int nr_pending;
-        int nr_waiting;
-        int nr_queued;
-        int barrier;
-        sector_t                next_resync;
-        int                     fullsync;  /* set to 1 if a full sync is needed,
-                                            * (fresh device added).
-                                            * Cleared when a sync completes.
-                                            */
-
-        wait_queue_head_t       wait_barrier;
-
-        mempool_t *r10bio_pool;
-        mempool_t *r10buf_pool;
-        struct page             *tmppage;
-};
-
-typedef struct r10_private_data_s conf_t;
-
-/*
- * this is the only point in the RAID code where we violate
- * C type safety. mddev->private is an 'opaque' pointer.
- */
-#define mddev_to_conf(mddev) ((conf_t *) mddev->private)
-
-/*
- * this is our 'private' RAID10 bio.
- *
- * it contains information about what kind of IO operations were started
- * for this RAID10 operation, and about their status:
- */
-
-struct r10bio_s {
-        atomic_t                remaining; /* 'have we finished' count,
-                                            * used from IRQ handlers
-                                            */
-        sector_t                sector; /* virtual sector number */
-        int                     sectors;
-        unsigned long           state;
-        mddev_t                 *mddev;
-        /*
-         * original bio going to /dev/mdx
-         */
-        struct bio              *master_bio;
-        /*
-         * if the IO is in READ direction, then this is where we read
-         */
-        int                     read_slot;
-
-        struct list_head        retry_list;
-        /*
-         * if the IO is in WRITE direction, then multiple bios are used,
-         * one for each copy.
-         * When resyncing we also use one for each copy.
-         * When reconstructing, we use 2 bios, one for read, one for write.
-         * We choose the number when they are allocated.
-         */
-        struct {
-                struct bio              *bio;
-                sector_t addr;
-                int devnum;
-        } devs[0];
-};
-
-/* when we get a read error on a read-only array, we redirect to another
- * device without failing the first device, or trying to over-write to
- * correct the read error.  To keep track of bad blocks on a per-bio
- * level, we store IO_BLOCKED in the appropriate 'bios' pointer
- */
-#define IO_BLOCKED ((struct bio*)1)
-
-/* bits for r10bio.state */
-#define R10BIO_Uptodate 0
-#define R10BIO_IsSync   1
-#define R10BIO_IsRecover 2
-#define R10BIO_Degraded 3
-#endif
diff --git a/include/linux/raid/raid5.h b/include/linux/raid/raid5.h
deleted file mode 100644
index 3b2672792457..000000000000
--- a/include/linux/raid/raid5.h
+++ /dev/null
@@ -1,402 +0,0 @@
-#ifndef _RAID5_H
-#define _RAID5_H
-
-#include <linux/raid/md.h>
-#include <linux/raid/xor.h>
-
-/*
- *
- * Each stripe contains one buffer per disc.  Each buffer can be in
- * one of a number of states stored in "flags".  Changes between
- * these states happen *almost* exclusively under a per-stripe
- * spinlock.  Some very specific changes can happen in bi_end_io, and
- * these are not protected by the spin lock.
- *
- * The flag bits that are used to represent these states are:
- *   R5_UPTODATE and R5_LOCKED
- *
- * State Empty == !UPTODATE, !LOCK
- *        We have no data, and there is no active request
- * State Want == !UPTODATE, LOCK
- *        A read request is being submitted for this block
- * State Dirty == UPTODATE, LOCK
- *        Some new data is in this buffer, and it is being written out
- * State Clean == UPTODATE, !LOCK
- *        We have valid data which is the same as on disc
- *
- * The possible state transitions are:
- *
- *  Empty -> Want   - on read or write to get old data for  parity calc
- *  Empty -> Dirty  - on compute_parity to satisfy write/sync request.(RECONSTRUCT_WRITE)
- *  Empty -> Clean  - on compute_block when computing a block for failed drive
- *  Want  -> Empty  - on failed read
- *  Want  -> Clean  - on successful completion of read request
- *  Dirty -> Clean  - on successful completion of write request
- *  Dirty -> Clean  - on failed write
- *  Clean -> Dirty  - on compute_parity to satisfy write/sync (RECONSTRUCT or RMW)
- *
- * The Want->Empty, Want->Clean, Dirty->Clean, transitions
- * all happen in b_end_io at interrupt time.
- * Each sets the Uptodate bit before releasing the Lock bit.
- * This leaves one multi-stage transition:
- *    Want->Dirty->Clean
- * This is safe because thinking that a Clean buffer is actually dirty
- * will at worst delay some action, and the stripe will be scheduled
- * for attention after the transition is complete.
- *
- * There is one possibility that is not covered by these states.  That
- * is if one drive has failed and there is a spare being rebuilt.  We
- * can't distinguish between a clean block that has been generated
- * from parity calculations, and a clean block that has been
- * successfully written to the spare ( or to parity when resyncing).
- * To distingush these states we have a stripe bit STRIPE_INSYNC that
- * is set whenever a write is scheduled to the spare, or to the parity
- * disc if there is no spare.  A sync request clears this bit, and
- * when we find it set with no buffers locked, we know the sync is
- * complete.
- *
- * Buffers for the md device that arrive via make_request are attached
- * to the appropriate stripe in one of two lists linked on b_reqnext.
- * One list (bh_read) for read requests, one (bh_write) for write.
- * There should never be more than one buffer on the two lists
- * together, but we are not guaranteed of that so we allow for more.
- *
- * If a buffer is on the read list when the associated cache buffer is
- * Uptodate, the data is copied into the read buffer and it's b_end_io
- * routine is called.  This may happen in the end_request routine only
- * if the buffer has just successfully been read.  end_request should
- * remove the buffers from the list and then set the Uptodate bit on
- * the buffer.  Other threads may do this only if they first check
- * that the Uptodate bit is set.  Once they have checked that they may
- * take buffers off the read queue.
- *
- * When a buffer on the write list is committed for write it is copied
- * into the cache buffer, which is then marked dirty, and moved onto a
- * third list, the written list (bh_written).  Once both the parity
- * block and the cached buffer are successfully written, any buffer on
- * a written list can be returned with b_end_io.
- *
- * The write list and read list both act as fifos.  The read list is
- * protected by the device_lock.  The write and written lists are
- * protected by the stripe lock.  The device_lock, which can be
- * claimed while the stipe lock is held, is only for list
- * manipulations and will only be held for a very short time.  It can
- * be claimed from interrupts.
- *
- *
- * Stripes in the stripe cache can be on one of two lists (or on
- * neither).  The "inactive_list" contains stripes which are not
- * currently being used for any request.  They can freely be reused
- * for another stripe.  The "handle_list" contains stripes that need
- * to be handled in some way.  Both of these are fifo queues.  Each
- * stripe is also (potentially) linked to a hash bucket in the hash
- * table so that it can be found by sector number.  Stripes that are
- * not hashed must be on the inactive_list, and will normally be at
- * the front.  All stripes start life this way.
- *
- * The inactive_list, handle_list and hash bucket lists are all protected by the
- * device_lock.
- *  - stripes on the inactive_list never have their stripe_lock held.
- *  - stripes have a reference counter. If count==0, they are on a list.
- *  - If a stripe might need handling, STRIPE_HANDLE is set.
- *  - When refcount reaches zero, then if STRIPE_HANDLE it is put on
- *    handle_list else inactive_list
- *
- * This, combined with the fact that STRIPE_HANDLE is only ever
- * cleared while a stripe has a non-zero count means that if the
- * refcount is 0 and STRIPE_HANDLE is set, then it is on the
- * handle_list and if recount is 0 and STRIPE_HANDLE is not set, then
- * the stripe is on inactive_list.
- *
- * The possible transitions are:
- *  activate an unhashed/inactive stripe (get_active_stripe())
- *     lockdev check-hash unlink-stripe cnt++ clean-stripe hash-stripe unlockdev
- *  activate a hashed, possibly active stripe (get_active_stripe())
- *     lockdev check-hash if(!cnt++)unlink-stripe unlockdev
- *  attach a request to an active stripe (add_stripe_bh())
- *     lockdev attach-buffer unlockdev
- *  handle a stripe (handle_stripe())
- *     lockstripe clrSTRIPE_HANDLE ...
- *              (lockdev check-buffers unlockdev) ..
- *              change-state ..
- *              record io/ops needed unlockstripe schedule io/ops
- *  release an active stripe (release_stripe())
- *     lockdev if (!--cnt) { if  STRIPE_HANDLE, add to handle_list else add to inactive-list } unlockdev
- *
- * The refcount counts each thread that have activated the stripe,
- * plus raid5d if it is handling it, plus one for each active request
- * on a cached buffer, and plus one if the stripe is undergoing stripe
- * operations.
- *
- * Stripe operations are performed outside the stripe lock,
- * the stripe operations are:
- * -copying data between the stripe cache and user application buffers
- * -computing blocks to save a disk access, or to recover a missing block
- * -updating the parity on a write operation (reconstruct write and
- *  read-modify-write)
- * -checking parity correctness
- * -running i/o to disk
- * These operations are carried out by raid5_run_ops which uses the async_tx
- * api to (optionally) offload operations to dedicated hardware engines.
- * When requesting an operation handle_stripe sets the pending bit for the
- * operation and increments the count.  raid5_run_ops is then run whenever
- * the count is non-zero.
- * There are some critical dependencies between the operations that prevent some
- * from being requested while another is in flight.
- * 1/ Parity check operations destroy the in cache version of the parity block,
- *    so we prevent parity dependent operations like writes and compute_blocks
- *    from starting while a check is in progress.  Some dma engines can perform
- *    the check without damaging the parity block, in these cases the parity
- *    block is re-marked up to date (assuming the check was successful) and is
- *    not re-read from disk.
- * 2/ When a write operation is requested we immediately lock the affected
- *    blocks, and mark them as not up to date.  This causes new read requests
- *    to be held off, as well as parity checks and compute block operations.
- * 3/ Once a compute block operation has been requested handle_stripe treats
- *    that block as if it is up to date.  raid5_run_ops guaruntees that any
- *    operation that is dependent on the compute block result is initiated after
- *    the compute block completes.
- */
-
-/*
- * Operations state - intermediate states that are visible outside of sh->lock
- * In general _idle indicates nothing is running, _run indicates a data
- * processing operation is active, and _result means the data processing result
- * is stable and can be acted upon.  For simple operations like biofill and
- * compute that only have an _idle and _run state they are indicated with
- * sh->state flags (STRIPE_BIOFILL_RUN and STRIPE_COMPUTE_RUN)
- */
-/**
- * enum check_states - handles syncing / repairing a stripe
- * @check_state_idle - check operations are quiesced
- * @check_state_run - check operation is running
- * @check_state_result - set outside lock when check result is valid
- * @check_state_compute_run - check failed and we are repairing
- * @check_state_compute_result - set outside lock when compute result is valid
- */
-enum check_states {
-        check_state_idle = 0,
-        check_state_run, /* parity check */
-        check_state_check_result,
-        check_state_compute_run, /* parity repair */
-        check_state_compute_result,
-};
-
-/**
- * enum reconstruct_states - handles writing or expanding a stripe
- */
-enum reconstruct_states {
-        reconstruct_state_idle = 0,
-        reconstruct_state_prexor_drain_run,     /* prexor-write */
-        reconstruct_state_drain_run,            /* write */
-        reconstruct_state_run,                  /* expand */
-        reconstruct_state_prexor_drain_result,
-        reconstruct_state_drain_result,
-        reconstruct_state_result,
-};
-
-struct stripe_head {
-        struct hlist_node       hash;
-        struct list_head        lru;                    /* inactive_list or handle_list */
-        struct raid5_private_data       *raid_conf;
-        sector_t                sector;                 /* sector of this row */
-        int                     pd_idx;                 /* parity disk index */
-        unsigned long           state;                  /* state flags */
-        atomic_t                count;                  /* nr of active thread/requests */
-        spinlock_t              lock;
-        int                     bm_seq; /* sequence number for bitmap flushes */
-        int                     disks;                  /* disks in stripe */
-        enum check_states       check_state;
-        enum reconstruct_states reconstruct_state;
-        /* stripe_operations
-         * @target - STRIPE_OP_COMPUTE_BLK target
-         */
-        struct stripe_operations {
-                int                target;
-                u32                zero_sum_result;
-        } ops;
-        struct r5dev {
-                struct bio      req;
-                struct bio_vec  vec;
-                struct page     *page;
-                struct bio      *toread, *read, *towrite, *written;
-                sector_t        sector;                 /* sector of this page */
-                unsigned long   flags;
-        } dev[1]; /* allocated with extra space depending of RAID geometry */
-};
-
-/* stripe_head_state - collects and tracks the dynamic state of a stripe_head
- *     for handle_stripe.  It is only valid under spin_lock(sh->lock);
- */
-struct stripe_head_state {
-        int syncing, expanding, expanded;
-        int locked, uptodate, to_read, to_write, failed, written;
-        int to_fill, compute, req_compute, non_overwrite;
-        int failed_num;
-        unsigned long ops_request;
-};
-
-/* r6_state - extra state data only relevant to r6 */
-struct r6_state {
-        int p_failed, q_failed, qd_idx, failed_num[2];
-};
-
-/* Flags */
-#define R5_UPTODATE     0       /* page contains current data */
-#define R5_LOCKED       1       /* IO has been submitted on "req" */
-#define R5_OVERWRITE    2       /* towrite covers whole page */
-/* and some that are internal to handle_stripe */
-#define R5_Insync       3       /* rdev && rdev->in_sync at start */
-#define R5_Wantread     4       /* want to schedule a read */
-#define R5_Wantwrite    5
-#define R5_Overlap      7       /* There is a pending overlapping request on this block */
-#define R5_ReadError    8       /* seen a read error here recently */
-#define R5_ReWrite      9       /* have tried to over-write the readerror */
-
-#define R5_Expanded     10      /* This block now has post-expand data */
-#define R5_Wantcompute  11 /* compute_block in progress treat as
-                                    * uptodate
-                                    */
-#define R5_Wantfill     12 /* dev->toread contains a bio that needs
-                                    * filling
-                                    */
-#define R5_Wantdrain    13 /* dev->towrite needs to be drained */
-/*
- * Write method
- */
-#define RECONSTRUCT_WRITE       1
-#define READ_MODIFY_WRITE       2
-/* not a write method, but a compute_parity mode */
-#define CHECK_PARITY            3
-
-/*
- * Stripe state
- */
-#define STRIPE_HANDLE           2
-#define STRIPE_SYNCING          3
-#define STRIPE_INSYNC           4
-#define STRIPE_PREREAD_ACTIVE   5
-#define STRIPE_DELAYED          6
-#define STRIPE_DEGRADED         7
-#define STRIPE_BIT_DELAY        8
-#define STRIPE_EXPANDING        9
-#define STRIPE_EXPAND_SOURCE    10
-#define STRIPE_EXPAND_READY     11
-#define STRIPE_IO_STARTED       12 /* do not count towards 'bypass_count' */
-#define STRIPE_FULL_WRITE       13 /* all blocks are set to be overwritten */
-#define STRIPE_BIOFILL_RUN      14
-#define STRIPE_COMPUTE_RUN      15
-/*
- * Operation request flags
- */
-#define STRIPE_OP_BIOFILL       0
-#define STRIPE_OP_COMPUTE_BLK   1
-#define STRIPE_OP_PREXOR        2
-#define STRIPE_OP_BIODRAIN      3
-#define STRIPE_OP_POSTXOR       4
-#define STRIPE_OP_CHECK 5
-
-/*
- * Plugging:
- *
- * To improve write throughput, we need to delay the handling of some
- * stripes until there has been a chance that several write requests
- * for the one stripe have all been collected.
- * In particular, any write request that would require pre-reading
- * is put on a "delayed" queue until there are no stripes currently
- * in a pre-read phase.  Further, if the "delayed" queue is empty when
- * a stripe is put on it then we "plug" the queue and do not process it
- * until an unplug call is made. (the unplug_io_fn() is called).
- *
- * When preread is initiated on a stripe, we set PREREAD_ACTIVE and add
- * it to the count of prereading stripes.
- * When write is initiated, or the stripe refcnt == 0 (just in case) we
- * clear the PREREAD_ACTIVE flag and decrement the count
- * Whenever the 'handle' queue is empty and the device is not plugged, we
- * move any strips from delayed to handle and clear the DELAYED flag and set
- * PREREAD_ACTIVE.
- * In stripe_handle, if we find pre-reading is necessary, we do it if
- * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue.
- * HANDLE gets cleared if stripe_handle leave nothing locked.
- */
- 
-
-struct disk_info {
-        mdk_rdev_t      *rdev;
-};
-
-struct raid5_private_data {
-        struct hlist_head       *stripe_hashtbl;
-        mddev_t                 *mddev;
-        struct disk_info        *spare;
-        int                     chunk_size, level, algorithm;
-        int                     max_degraded;
-        int                     raid_disks;
-        int                     max_nr_stripes;
-
-        /* used during an expand */
-        sector_t                expand_progress;        /* MaxSector when no expand happening */
-        sector_t                expand_lo; /* from here up to expand_progress it out-of-bounds
-                                            * as we haven't flushed the metadata yet
-                                            */
-        int                     previous_raid_disks;
-
-        struct list_head        handle_list; /* stripes needing handling */
-        struct list_head        hold_list; /* preread ready stripes */
-        struct list_head        delayed_list; /* stripes that have plugged requests */
-        struct list_head        bitmap_list; /* stripes delaying awaiting bitmap update */
-        struct bio              *retry_read_aligned; /* currently retrying aligned bios   */
-        struct bio              *retry_read_aligned_list; /* aligned bios retry list  */
-        atomic_t                preread_active_stripes; /* stripes with scheduled io */
-        atomic_t                active_aligned_reads;
-        atomic_t                pending_full_writes; /* full write backlog */
-        int                     bypass_count; /* bypassed prereads */
-        int                     bypass_threshold; /* preread nice */
-        struct list_head        *last_hold; /* detect hold_list promotions */
-
-        atomic_t                reshape_stripes; /* stripes with pending writes for reshape */
-        /* unfortunately we need two cache names as we temporarily have
-         * two caches.
-         */
-        int                     active_name;
-        char                    cache_name[2][20];
-        struct kmem_cache               *slab_cache; /* for allocating stripes */
-
-        int                     seq_flush, seq_write;
-        int                     quiesce;
-
-        int                     fullsync;  /* set to 1 if a full sync is needed,
-                                            * (fresh device added).
-                                            * Cleared when a sync completes.
-                                            */
-
-        struct page             *spare_page; /* Used when checking P/Q in raid6 */
-
-        /*
-         * Free stripes pool
-         */
-        atomic_t                active_stripes;
-        struct list_head        inactive_list;
-        wait_queue_head_t       wait_for_stripe;
-        wait_queue_head_t       wait_for_overlap;
-        int                     inactive_blocked;       /* release of inactive stripes blocked,
-                                                         * waiting for 25% to be free
-                                                         */
-        int                     pool_size; /* number of disks in stripeheads in pool */
-        spinlock_t              device_lock;
-        struct disk_info        *disks;
-};
-
-typedef struct raid5_private_data raid5_conf_t;
-
-#define mddev_to_conf(mddev) ((raid5_conf_t *) mddev->private)
-
-/*
- * Our supported algorithms
- */
-#define ALGORITHM_LEFT_ASYMMETRIC       0
-#define ALGORITHM_RIGHT_ASYMMETRIC      1
-#define ALGORITHM_LEFT_SYMMETRIC        2
-#define ALGORITHM_RIGHT_SYMMETRIC       3
-
-#endif
diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h
index 3e120587eada..5a210959e3f8 100644
--- a/include/linux/raid/xor.h
+++ b/include/linux/raid/xor.h
@@ -1,8 +1,6 @@
 #ifndef _XOR_H
 #define _XOR_H
 
-#include <linux/raid/md.h>
-
 #define MAX_XOR_BLOCKS 4
 
 extern void xor_blocks(unsigned int count, unsigned int bytes,
diff --git a/include/linux/regulator/bq24022.h b/include/linux/regulator/bq24022.h
index e84b0a9feda5..a6d014005d49 100644
--- a/include/linux/regulator/bq24022.h
+++ b/include/linux/regulator/bq24022.h
@@ -10,6 +10,8 @@
  *
  */
 
+struct regulator_init_data;
+
 /**
  * bq24022_mach_info - platform data for bq24022
  * @gpio_nce: GPIO line connected to the nCE pin, used to enable / disable charging
@@ -18,4 +20,5 @@
 struct bq24022_mach_info {
         int gpio_nce;
         int gpio_iset2;
+        struct regulator_init_data *init_data;
 };
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 801bf77ff4e2..277f4b964df5 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
  *
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -88,6 +88,7 @@
  * FAIL           Regulator output has failed.
  * OVER_TEMP      Regulator over temp.
  * FORCE_DISABLE  Regulator shut down by software.
+ * VOLTAGE_CHANGE Regulator voltage changed.
  *
  * NOTE: These events can be OR'ed together when passed into handler.
  */
@@ -98,6 +99,7 @@
 #define REGULATOR_EVENT_FAIL                    0x08
 #define REGULATOR_EVENT_OVER_TEMP               0x10
 #define REGULATOR_EVENT_FORCE_DISABLE           0x20
+#define REGULATOR_EVENT_VOLTAGE_CHANGE          0x40
 
 struct regulator;
 
@@ -140,6 +142,8 @@ int regulator_bulk_disable(int num_consumers,
 void regulator_bulk_free(int num_consumers,
                          struct regulator_bulk_data *consumers);
 
+int regulator_count_voltages(struct regulator *regulator);
+int regulator_list_voltage(struct regulator *regulator, unsigned selector);
 int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV);
 int regulator_get_voltage(struct regulator *regulator);
 int regulator_set_current_limit(struct regulator *regulator,
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 2dae05705f13..4848d8dacd90 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
  *
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -21,25 +21,38 @@
 struct regulator_dev;
 struct regulator_init_data;
 
+enum regulator_status {
+        REGULATOR_STATUS_OFF,
+        REGULATOR_STATUS_ON,
+        REGULATOR_STATUS_ERROR,
+        /* fast/normal/idle/standby are flavors of "on" */
+        REGULATOR_STATUS_FAST,
+        REGULATOR_STATUS_NORMAL,
+        REGULATOR_STATUS_IDLE,
+        REGULATOR_STATUS_STANDBY,
+};
+
 /**
  * struct regulator_ops - regulator operations.
  *
- * This struct describes regulator operations which can be implemented by
- * regulator chip drivers.
- *
- * @enable: Enable the regulator.
- * @disable: Disable the regulator.
+ * @enable: Configure the regulator as enabled.
+ * @disable: Configure the regulator as disabled.
  * @is_enabled: Return 1 if the regulator is enabled, 0 otherwise.
  *
  * @set_voltage: Set the voltage for the regulator within the range specified.
  *               The driver should select the voltage closest to min_uV.
  * @get_voltage: Return the currently configured voltage for the regulator.
+ * @list_voltage: Return one of the supported voltages, in microvolts; zero
+ *      if the selector indicates a voltage that is unusable on this system;
+ *      or negative errno.  Selectors range from zero to one less than
+ *      regulator_desc.n_voltages.  Voltages may be reported in any order.
  *
  * @set_current_limit: Configure a limit for a current-limited regulator.
- * @get_current_limit: Get the limit for a current-limited regulator.
+ * @get_current_limit: Get the configured limit for a current-limited regulator.
  *
- * @set_mode: Set the operating mode for the regulator.
- * @get_mode: Get the current operating mode for the regulator.
+ * @get_mode: Get the configured operating mode for the regulator.
+ * @get_status: Return actual (not as-configured) status of regulator, as a
+ *      REGULATOR_STATUS value (or negative errno)
  * @get_optimum_mode: Get the most efficient operating mode for the regulator
  *                    when running with the specified parameters.
  *
@@ -51,9 +64,15 @@ struct regulator_init_data;
  *                       suspended.
  * @set_suspend_mode: Set the operating mode for the regulator when the
  *                    system is suspended.
+ *
+ * This struct describes regulator operations which can be implemented by
+ * regulator chip drivers.
  */
 struct regulator_ops {
 
+        /* enumerate supported voltages */
+        int (*list_voltage) (struct regulator_dev *, unsigned selector);
+
         /* get/set regulator voltage */
         int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV);
         int (*get_voltage) (struct regulator_dev *);
@@ -72,6 +91,13 @@ struct regulator_ops {
         int (*set_mode) (struct regulator_dev *, unsigned int mode);
         unsigned int (*get_mode) (struct regulator_dev *);
 
+        /* report regulator status ... most other accessors report
+         * control inputs, this reports results of combining inputs
+         * from Linux (and other sources) with the actual load.
+         * returns REGULATOR_STATUS_* or negative errno.
+         */
+        int (*get_status)(struct regulator_dev *);
+
         /* get most efficient regulator operating mode for load */
         unsigned int (*get_optimum_mode) (struct regulator_dev *, int input_uV,
                                           int output_uV, int load_uA);
@@ -106,6 +132,7 @@ enum regulator_type {
  *
  * @name: Identifying name for the regulator.
  * @id: Numerical identifier for the regulator.
+ * @n_voltages: Number of selectors available for ops.list_voltage().
  * @ops: Regulator operations table.
  * @irq: Interrupt number for the regulator.
  * @type: Indicates if the regulator is a voltage or current regulator.
@@ -114,14 +141,48 @@ enum regulator_type {
 struct regulator_desc {
         const char *name;
         int id;
+        unsigned n_voltages;
         struct regulator_ops *ops;
         int irq;
         enum regulator_type type;
         struct module *owner;
 };
 
+/*
+ * struct regulator_dev
+ *
+ * Voltage / Current regulator class device. One for each
+ * regulator.
+ *
+ * This should *not* be used directly by anything except the regulator
+ * core and notification injection (which should take the mutex and do
+ * no other direct access).
+ */
+struct regulator_dev {
+        struct regulator_desc *desc;
+        int use_count;
+
+        /* lists we belong to */
+        struct list_head list; /* list of all regulators */
+        struct list_head slist; /* list of supplied regulators */
+
+        /* lists we own */
+        struct list_head consumer_list; /* consumers we supply */
+        struct list_head supply_list; /* regulators we supply */
+
+        struct blocking_notifier_head notifier;
+        struct mutex mutex; /* consumer lock */
+        struct module *owner;
+        struct device dev;
+        struct regulation_constraints *constraints;
+        struct regulator_dev *supply;   /* for tree */
+
+        void *reg_data;         /* regulator_dev data */
+};
+
 struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
-        struct device *dev, void *driver_data);
+        struct device *dev, struct regulator_init_data *init_data,
+        void *driver_data);
 void regulator_unregister(struct regulator_dev *rdev);
 
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h
index 1387a5d2190e..91b4da31f1b5 100644
--- a/include/linux/regulator/fixed.h
+++ b/include/linux/regulator/fixed.h
@@ -14,9 +14,12 @@
 #ifndef __REGULATOR_FIXED_H
 #define __REGULATOR_FIXED_H
 
+struct regulator_init_data;
+
 struct fixed_voltage_config {
         const char *supply_name;
         int microvolts;
+        struct regulator_init_data *init_data;
 };
 
 #endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 3794773b23d2..bac64fa390f2 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
  *
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -73,7 +73,9 @@ struct regulator_state {
  *
  * @always_on: Set if the regulator should never be disabled.
  * @boot_on: Set if the regulator is enabled when the system is initially
- *           started.
+ *           started.  If the regulator is not enabled by the hardware or
+ *           bootloader then it will be enabled when the constraints are
+ *           applied.
  * @apply_uV: Apply the voltage constraint when initialising.
  *
  * @input_uV: Input voltage for regulator when supplied by another regulator.
@@ -83,6 +85,7 @@ struct regulator_state {
  * @state_standby: State for regulator when system is suspended in standby
  *                 mode.
  * @initial_state: Suspend state to set by default.
+ * @initial_mode: Mode to set at startup.
  */
 struct regulation_constraints {
 
@@ -111,6 +114,9 @@ struct regulation_constraints {
         struct regulator_state state_standby;
         suspend_state_t initial_state; /* suspend state to set at init */
 
+        /* mode to set on startup */
+        unsigned int initial_mode;
+
         /* constriant flags */
         unsigned always_on:1;   /* regulator never off when system is on */
         unsigned boot_on:1;     /* bootloader/firmware enabled regulator */
@@ -160,4 +166,6 @@ struct regulator_init_data {
 
 int regulator_suspend_prepare(suspend_state_t state);
 
+void regulator_has_full_constraints(void);
+
 #endif
diff --git a/include/linux/rtc-v3020.h b/include/linux/rtc-v3020.h
index bf74e63c98fe..8ba646e610d9 100644
--- a/include/linux/rtc-v3020.h
+++ b/include/linux/rtc-v3020.h
@@ -14,6 +14,12 @@
  * is used depends on the board. */
 struct v3020_platform_data {
         int leftshift; /* (1<<(leftshift)) & readl() */
+
+        int use_gpio:1;
+        unsigned int gpio_cs;
+        unsigned int gpio_wr;
+        unsigned int gpio_rd;
+        unsigned int gpio_io;
 };
 
 #define V3020_STATUS_0  0x00
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5a50fdef5be5..b94f3541f67b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -68,7 +68,7 @@ struct sched_param {
 #include <linux/smp.h>
 #include <linux/sem.h>
 #include <linux/signal.h>
-#include <linux/fs_struct.h>
+#include <linux/path.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
 #include <linux/pid.h>
@@ -97,6 +97,7 @@ struct futex_pi_state;
 struct robust_list_head;
 struct bio;
 struct bts_tracer;
+struct fs_struct;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -549,25 +550,8 @@ struct signal_struct {
 
         struct list_head cpu_timers[3];
 
-        /* job control IDs */
-
-        /*
-         * pgrp and session fields are deprecated.
-         * use the task_session_Xnr and task_pgrp_Xnr routines below
-         */
-
-        union {
-                pid_t pgrp __deprecated;
-                pid_t __pgrp;
-        };
-
         struct pid *tty_old_pgrp;
 
-        union {
-                pid_t session __deprecated;
-                pid_t __session;
-        };
-
         /* boolean value for session group leader */
         int leader;
 
@@ -1473,16 +1457,6 @@ static inline int rt_task(struct task_struct *p)
         return rt_prio(p->prio);
 }
 
-static inline void set_task_session(struct task_struct *tsk, pid_t session)
-{
-        tsk->signal->__session = session;
-}
-
-static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp)
-{
-        tsk->signal->__pgrp = pgrp;
-}
-
 static inline struct pid *task_pid(struct task_struct *task)
 {
         return task->pids[PIDTYPE_PID].pid;
@@ -1493,6 +1467,11 @@ static inline struct pid *task_tgid(struct task_struct *task)
         return task->group_leader->pids[PIDTYPE_PID].pid;
 }
 
+/*
+ * Without tasklist or rcu lock it is not safe to dereference
+ * the result of task_pgrp/task_session even if task == current,
+ * we can race with another thread doing sys_setsid/sys_setpgid.
+ */
 static inline struct pid *task_pgrp(struct task_struct *task)
 {
         return task->group_leader->pids[PIDTYPE_PGID].pid;
@@ -1518,17 +1497,23 @@ struct pid_namespace;
  *
  * see also pid_nr() etc in include/linux/pid.h
  */
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
+                        struct pid_namespace *ns);
 
 static inline pid_t task_pid_nr(struct task_struct *tsk)
 {
         return tsk->pid;
 }
 
-pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
+static inline pid_t task_pid_nr_ns(struct task_struct *tsk,
+                                        struct pid_namespace *ns)
+{
+        return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
+}
 
 static inline pid_t task_pid_vnr(struct task_struct *tsk)
 {
-        return pid_vnr(task_pid(tsk));
+        return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
 }
 
 
@@ -1545,31 +1530,34 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
-static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
+                                        struct pid_namespace *ns)
 {
-        return tsk->signal->__pgrp;
+        return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
 }
 
-pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
 static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
 {
-        return pid_vnr(task_pgrp(tsk));
+        return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
 }
 
 
-static inline pid_t task_session_nr(struct task_struct *tsk)
+static inline pid_t task_session_nr_ns(struct task_struct *tsk,
+                                        struct pid_namespace *ns)
 {
-        return tsk->signal->__session;
+        return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
 }
 
-pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
 static inline pid_t task_session_vnr(struct task_struct *tsk)
 {
-        return pid_vnr(task_session(tsk));
+        return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
+/* obsolete, do not use */
+static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+{
+        return task_pgrp_nr_ns(tsk, &init_pid_ns);
+}
 
 /**
  * pid_alive - check that a task structure is not stale
@@ -1979,7 +1967,8 @@ extern void mm_release(struct task_struct *, struct mm_struct *);
 /* Allocate a new mm structure and copy contents from tsk->mm */
 extern struct mm_struct *dup_mm(struct task_struct *tsk);
 
-extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
+extern int copy_thread(unsigned long, unsigned long, unsigned long,
+                        struct task_struct *, struct pt_regs *);
 extern void flush_thread(void);
 extern void exit_thread(void);
 
@@ -2064,6 +2053,11 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
                 (thread_group_leader(p) && !thread_group_empty(p))
 
+static inline int task_detached(struct task_struct *p)
+{
+        return p->exit_signal == -1;
+}
+
 /*
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h
new file mode 100644
index 000000000000..85958277f83d
--- /dev/null
+++ b/include/linux/slow-work.h
@@ -0,0 +1,95 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#ifndef _LINUX_SLOW_WORK_H
+#define _LINUX_SLOW_WORK_H
+
+#ifdef CONFIG_SLOW_WORK
+
+#include <linux/sysctl.h>
+
+struct slow_work;
+
+/*
+ * The operations used to support slow work items
+ */
+struct slow_work_ops {
+        /* get a ref on a work item
+         * - return 0 if successful, -ve if not
+         */
+        int (*get_ref)(struct slow_work *work);
+
+        /* discard a ref to a work item */
+        void (*put_ref)(struct slow_work *work);
+
+        /* execute a work item */
+        void (*execute)(struct slow_work *work);
+};
+
+/*
+ * A slow work item
+ * - A reference is held on the parent object by the thread pool when it is
+ *   queued
+ */
+struct slow_work {
+        unsigned long           flags;
+#define SLOW_WORK_PENDING       0       /* item pending (further) execution */
+#define SLOW_WORK_EXECUTING     1       /* item currently executing */
+#define SLOW_WORK_ENQ_DEFERRED  2       /* item enqueue deferred */
+#define SLOW_WORK_VERY_SLOW     3       /* item is very slow */
+        const struct slow_work_ops *ops; /* operations table for this item */
+        struct list_head        link;   /* link in queue */
+};
+
+/**
+ * slow_work_init - Initialise a slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a slow work item.
+ */
+static inline void slow_work_init(struct slow_work *work,
+                                  const struct slow_work_ops *ops)
+{
+        work->flags = 0;
+        work->ops = ops;
+        INIT_LIST_HEAD(&work->link);
+}
+
+/**
+ * slow_work_init - Initialise a very slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a very slow work item.  This item will be restricted such that
+ * only a certain number of the pool threads will be able to execute items of
+ * this type.
+ */
+static inline void vslow_work_init(struct slow_work *work,
+                                   const struct slow_work_ops *ops)
+{
+        work->flags = 1 << SLOW_WORK_VERY_SLOW;
+        work->ops = ops;
+        INIT_LIST_HEAD(&work->link);
+}
+
+extern int slow_work_enqueue(struct slow_work *work);
+extern int slow_work_register_user(void);
+extern void slow_work_unregister_user(void);
+
+#ifdef CONFIG_SYSCTL
+extern ctl_table slow_work_sysctls[];
+#endif
+
+#endif /* CONFIG_SLOW_WORK */
+#endif /* _LINUX_SLOW_WORK_H */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index bbacb7baa446..a69db820eed6 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -38,7 +38,7 @@ int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
 /*
  * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc.
  * (defined in asm header):
- */ 
+ */
 
 /*
  * stops all CPUs but the current one:
@@ -82,7 +82,8 @@ smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
         return 0;
 }
 
-void __smp_call_function_single(int cpuid, struct call_single_data *data);
+void __smp_call_function_single(int cpuid, struct call_single_data *data,
+                                int wait);
 
 /*
  * Generic and arch helpers
@@ -121,6 +122,8 @@ extern unsigned int setup_max_cpus;
 
 #else /* !SMP */
 
+static inline void smp_send_stop(void) { }
+
 /*
  *      These macros fold the SMP functionality into a single CPU system
  */
diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h
index 1085212c446e..306e7b1c69ed 100644
--- a/include/linux/spi/eeprom.h
+++ b/include/linux/spi/eeprom.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_SPI_EEPROM_H
 #define __LINUX_SPI_EEPROM_H
 
+#include <linux/memory.h>
+
 /*
  * Put one of these structures in platform_data for SPI EEPROMS handled
  * by the "at25" driver.  On SPI, most EEPROMS understand the same core
@@ -17,6 +19,10 @@ struct spi_eeprom {
 #define EE_ADDR2        0x0002                  /* 16 bit addrs */
 #define EE_ADDR3        0x0004                  /* 24 bit addrs */
 #define EE_READONLY     0x0008                  /* disallow writes */
+
+        /* for exporting this chip's data to other kernel code */
+        void (*setup)(struct memory_accessor *mem, void *context);
+        void *context;
 };
 
 #endif /* __LINUX_SPI_EEPROM_H */
diff --git a/include/linux/spi/spi_gpio.h b/include/linux/spi/spi_gpio.h
index 0f01a0f1f40c..ca6782ee4b9f 100644
--- a/include/linux/spi/spi_gpio.h
+++ b/include/linux/spi/spi_gpio.h
@@ -25,10 +25,16 @@
  *      ...
  *      };
  *
+ * If chipselect is not used (there's only one device on the bus), assign
+ * SPI_GPIO_NO_CHIPSELECT to the controller_data:
+ *              .controller_data = (void *) SPI_GPIO_NO_CHIPSELECT;
+ *
  * If the bitbanged bus is later switched to a "native" controller,
  * that platform_device and controller_data should be removed.
  */
 
+#define SPI_GPIO_NO_CHIPSELECT          ((unsigned long)-1l)
+
 /**
  * struct spi_gpio_platform_data - parameter for bitbanged SPI master
  * @sck: number of the GPIO used for clock output
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index a0c66a2e00ad..252b245cfcf4 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -153,9 +153,11 @@ do {								\
  extern int _raw_spin_trylock(spinlock_t *lock);
  extern void _raw_spin_unlock(spinlock_t *lock);
  extern void _raw_read_lock(rwlock_t *lock);
+#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock)
  extern int _raw_read_trylock(rwlock_t *lock);
  extern void _raw_read_unlock(rwlock_t *lock);
  extern void _raw_write_lock(rwlock_t *lock);
+#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock)
  extern int _raw_write_trylock(rwlock_t *lock);
  extern void _raw_write_unlock(rwlock_t *lock);
 #else
@@ -165,9 +167,13 @@ do {								\
 # define _raw_spin_trylock(lock)        __raw_spin_trylock(&(lock)->raw_lock)
 # define _raw_spin_unlock(lock)         __raw_spin_unlock(&(lock)->raw_lock)
 # define _raw_read_lock(rwlock)         __raw_read_lock(&(rwlock)->raw_lock)
+# define _raw_read_lock_flags(lock, flags) \
+                __raw_read_lock_flags(&(lock)->raw_lock, *(flags))
 # define _raw_read_trylock(rwlock)      __raw_read_trylock(&(rwlock)->raw_lock)
 # define _raw_read_unlock(rwlock)       __raw_read_unlock(&(rwlock)->raw_lock)
 # define _raw_write_lock(rwlock)        __raw_write_lock(&(rwlock)->raw_lock)
+# define _raw_write_lock_flags(lock, flags) \
+                __raw_write_lock_flags(&(lock)->raw_lock, *(flags))
 # define _raw_write_trylock(rwlock)     __raw_write_trylock(&(rwlock)->raw_lock)
 # define _raw_write_unlock(rwlock)      __raw_write_unlock(&(rwlock)->raw_lock)
 #endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 3c877d686375..489019ef1694 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -122,5 +122,14 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4);
 extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
                         const void *from, size_t available);
 
+/**
+ * strstarts - does @str start with @prefix?
+ * @str: string to examine
+ * @prefix: prefix to look for.
+ */
+static inline bool strstarts(const char *str, const char *prefix)
+{
+        return strncmp(str, prefix, strlen(prefix)) == 0;
+}
 #endif
 #endif /* _LINUX_STRING_H_ */
diff --git a/include/linux/synclink.h b/include/linux/synclink.h
index 99b8bdb17b2b..0ff2779c44d0 100644
--- a/include/linux/synclink.h
+++ b/include/linux/synclink.h
@@ -125,6 +125,7 @@
 #define MGSL_MODE_MONOSYNC      3
 #define MGSL_MODE_BISYNC        4
 #define MGSL_MODE_RAW           6
+#define MGSL_MODE_BASE_CLOCK    7
 
 #define MGSL_BUS_TYPE_ISA       1
 #define MGSL_BUS_TYPE_EISA      2
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 0cff9bb80b02..6470f74074af 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -517,6 +517,10 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf,
                             size_t count, loff_t pos);
 asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
                              size_t count, loff_t pos);
+asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec,
+                           unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
+asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec,
+                            unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
 asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
 asmlinkage long sys_mkdir(const char __user *pathname, int mode);
 asmlinkage long sys_chdir(const char __user *filename);
diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h
index dd253177f65f..3e08a1c86830 100644
--- a/include/linux/timeriomem-rng.h
+++ b/include/linux/timeriomem-rng.h
@@ -14,7 +14,7 @@ struct timeriomem_rng_data {
         struct completion       completion;
         unsigned int            present:1;
 
-        u32 __iomem             *address;
+        void __iomem            *address;
 
         /* measures in usecs */
         unsigned int            period;
diff --git a/include/linux/topology.h b/include/linux/topology.h
index a16b9e06f2e5..7402c1a27c4f 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -38,11 +38,7 @@
 #endif
 
 #ifndef nr_cpus_node
-#define nr_cpus_node(node)                              \
-        ({                                              \
-                node_to_cpumask_ptr(__tmp__, node);     \
-                cpus_weight(*__tmp__);                  \
-        })
+#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
 #endif
 
 #define for_each_node_with_cpus(node)                   \
@@ -200,4 +196,9 @@ int arch_update_cpu_topology(void);
 #define topology_core_cpumask(cpu)              cpumask_of(cpu)
 #endif
 
+/* Returns the number of the current Node. */
+#ifndef numa_node_id
+#define numa_node_id()          (cpu_to_node(raw_smp_processor_id()))
+#endif
+
 #endif /* _LINUX_TOPOLOGY_H */
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 6186a789d6c7..c7aa154f4bfc 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -388,17 +388,14 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info,
  * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal
  * @task:               task receiving the signal
  * @sig:                signal number being sent
- * @handler:            %SIG_IGN or %SIG_DFL
  *
  * Return zero iff tracing doesn't care to examine this ignored signal,
  * so it can short-circuit normal delivery and never even get queued.
- * Either @handler is %SIG_DFL and @sig's default is ignore, or it's %SIG_IGN.
  *
  * Called with @task->sighand->siglock held.
  */
 static inline int tracehook_consider_ignored_signal(struct task_struct *task,
-                                                    int sig,
-                                                    void __user *handler)
+                                                    int sig)
 {
         return (task_ptrace(task) & PT_PTRACED) != 0;
 }
@@ -407,19 +404,17 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task,
  * tracehook_consider_fatal_signal - suppress special handling of fatal signal
  * @task:               task receiving the signal
  * @sig:                signal number being sent
- * @handler:            %SIG_DFL or %SIG_IGN
  *
  * Return nonzero to prevent special handling of this termination signal.
- * Normally @handler is %SIG_DFL.  It can be %SIG_IGN if @sig is ignored,
- * in which case force_sig() is about to reset it to %SIG_DFL.
+ * Normally handler for signal is %SIG_DFL.  It can be %SIG_IGN if @sig is
+ * ignored, in which case force_sig() is about to reset it to %SIG_DFL.
  * When this returns zero, this signal might cause a quick termination
  * that does not give the debugger a chance to intercept the signal.
  *
  * Called with or without @task->sighand->siglock held.
  */
 static inline int tracehook_consider_fatal_signal(struct task_struct *task,
-                                                  int sig,
-                                                  void __user *handler)
+                                                  int sig)
 {
         return (task_ptrace(task) & PT_PTRACED) != 0;
 }
@@ -507,7 +502,7 @@ static inline int tracehook_notify_jctl(int notify, int why)
 static inline int tracehook_notify_death(struct task_struct *task,
                                          void **death_cookie, int group_dead)
 {
-        if (task->exit_signal == -1)
+        if (task_detached(task))
                 return task->ptrace ? SIGCHLD : DEATH_REAP;
 
         /*
diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h
index 5f401b644ed5..429c631d2aad 100644
--- a/include/linux/usb/wusb.h
+++ b/include/linux/usb/wusb.h
@@ -80,8 +80,7 @@ struct wusb_ckhdid {
         u8 data[16];
 } __attribute__((packed));
 
-const static
-struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } };
+static const struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } };
 
 #define WUSB_CKHDID_STRSIZE (3 * sizeof(struct wusb_ckhdid) + 1)
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 3cd51e579ab1..13e1adf55c4c 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -41,6 +41,11 @@ struct delayed_work {
         struct timer_list timer;
 };
 
+static inline struct delayed_work *to_delayed_work(struct work_struct *work)
+{
+        return container_of(work, struct delayed_work, work);
+}
+
 struct execute_work {
         struct work_struct work;
 };